© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 11342
    Prev
    Next
    INDEX
    Explanations

    HTML elements related to web page layout and structure

    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
    223
    +0.12
    0.4%
    286
    +0.11
    0.4%
    73
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.12
    0.02
    113
    +0.11
    0.01
    289
    +0.10
    0.01
    Negative Logits
    SEE
    -1.00
     afore
    -0.91
     Infrastructure
    -0.88
    ges
    -0.87
     Clover
    -0.85
    chnology
    -0.84
     Sins
    -0.82
    laus
    -0.79
     Cosponsors
    -0.78
     Admir
    -0.78
    POSITIVE LOGITS
    ault
    1.27
    isible
    1.24
    isions
    1.11
    ination
    1.09
    inyl
    1.06
    ><
    1.05
    inity
    1.04
    ag
    1.03
    acent
    1.03
    arian
    1.03
    Activations Density 0.039%

    No Known Activations