© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35998
    Prev
    Next
    INDEX
    Explanations

    references to speed, efficiency, advancements, or improvements in various contexts, including technological progress, software development, energy efficiency, and athletic performance

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    0.9%
    326
    +0.12
    0.5%
    60
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.21
    0.08
    269
    +0.12
    0.06
    271
    +0.12
    0.04
    Negative Logits
    mberg
    -0.93
    liga
    -0.91
    algia
    -0.80
    gypt
    -0.76
     Shame
    -0.74
    vironment
    -0.74
    rights
    -0.72
    ortium
    -0.72
    arov
    -0.72
    rien
    -0.71
    POSITIVE LOGITS
     paced
    1.30
    idious
    1.16
     speeds
    1.02
     lear
    0.98
     turnaround
    0.93
     Faster
    0.86
     acceleration
    0.86
     speed
    0.86
     than
    0.85
     acceler
    0.81
    Activations Density 8.064%

    No Known Activations