© 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. 12897
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and places

    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
    585
    +0.04
    0.5%
    373
    +0.04
    0.4%
    286
    +0.04
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.04
    0.07
    232
    +0.04
    0.06
    538
    +0.04
    0.05
    Negative Logits
    geon
    -0.30
    ractor
    -0.30
     crochet
    -0.27
    VIEW
    -0.27
    ©¶æ
    -0.27
    utenant
    -0.27
    geoning
    -0.26
     Fired
    -0.26
    RG
    -0.26
    fired
    -0.26
    POSITIVE LOGITS
    andro
    0.37
    ilon
    0.33
    entric
    0.32
    ario
    0.31
    andra
    0.31
    utical
    0.31
    mson
    0.30
    reon
    0.30
    ida
    0.30
    ilo
    0.29
    Activations Density 0.481%

    No Known Activations