© 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. 7208
    Prev
    Next
    INDEX
    Explanations

    links to specific Wikipedia pages or full URLs

    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
    407
    +0.17
    0.6%
    483
    +0.14
    0.5%
    652
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.17
    0.05
    477
    +0.14
    0.04
    586
    +0.14
    0.04
    Negative Logits
    rament
    -0.89
    milo
    -0.85
    ĪĴ
    -0.84
    buquerque
    -0.83
    paio
    -0.82
    Answer
    -0.80
     âī¡
    -0.79
    Initialized
    -0.79
    asar
    -0.77
     Aires
    -0.76
    POSITIVE LOGITS
    /#
    1.26
    /?
    1.14
    /-
    1.05
    biz
    1.04
    php
    1.02
    cdn
    0.94
    /
    0.94
    /_
    0.93
    nw
    0.91
     tc
    0.91
    Activations Density 0.202%

    No Known Activations