© 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. 6713
    Prev
    Next
    INDEX
    Explanations

    timestamps from logs

    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
    101
    +0.15
    0.5%
    326
    +0.15
    0.5%
    274
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.05
    568
    +0.15
    0.04
    6
    +0.15
    0.05
    Negative Logits
    ulet
    -1.20
     pse
    -1.14
    foundland
    -1.04
    ufact
    -1.00
     endors
    -1.00
    reon
    -0.99
    udeb
    -0.96
     conclud
    -0.95
     nodd
    -0.94
     hemor
    -0.93
    POSITIVE LOGITS
    PM
    1.29
    Ur
    1.10
    AM
    1.10
    pm
    1.09
    GMT
    1.07
    Interstitial
    1.03
    OPA
    0.99
    AMS
    0.98
    ACTED
    0.97
     pm
    0.96
    Activations Density 0.579%

    No Known Activations