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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4714
    Prev
    Next
    INDEX
    Explanations

    patterns related to data analysis, including terms like "sample," "location," and "zone," along with mathematical concepts and programming-related terms

    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
    +0.25
    1.2%
    481
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.25
    0.10
    678
    +0.10
    0.11
    160
    +0.10
    0.20
    Negative Logits
    hur
    -0.76
    Company
    -0.69
    HUD
    -0.69
    panic
    -0.64
    Hit
    -0.60
    ãĥĬ
    -0.59
     weap
    -0.59
    Cash
    -0.58
    Americans
    -0.58
     Zombies
    -0.57
    POSITIVE LOGITS
    pole
    0.91
     Layout
    0.84
     boundary
    0.78
     containing
    0.76
     diameter
    0.75
     Contents
    0.74
    mates
    0.74
     width
    0.73
     Door
    0.72
     separating
    0.72
    Activations Density 10.856%

    No Known Activations