© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6161
    Prev
    Next
    INDEX
    Explanations

    technical information related to software updates and bug fixes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    640
    +0.28
    1.0%
    447
    +0.21
    0.8%
    393
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.15
    6
    +0.21
    0.13
    176
    +0.17
    0.06
    Negative Logits
    TPPStreamerBot
    -1.01
    ryce
    -0.86
    inement
    -0.86
    formation
    -0.86
    etheless
    -0.84
    onson
    -0.84
    wagen
    -0.83
    conference
    -0.80
    belt
    -0.79
    adjusted
    -0.79
    POSITIVE LOGITS
     Inher
    1.07
     Same
    1.03
     Ibid
    0.97
     Unt
    0.95
     Beware
    0.95
     Unable
    0.94
     Selected
    0.93
     Eas
    0.93
     Written
    0.92
     Learns
    0.91
    Activations Density 2.603%

    No Known Activations