Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 653
    Prev
    Next
    INDEX
    Explanations

    names related to professional cycling teams

    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
    33
    +0.09
    0.6%
    710
    +0.08
    0.5%
    634
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.09
    0.03
    616
    +0.08
    0.02
    659
    +0.08
    0.02
    Negative Logits
    assetsadobe
    -0.68
    isSpecialOrderable
    -0.56
    SIGN
    -0.52
    channelAvailability
    -0.50
    heric
    -0.50
    wcs
    -0.50
    adobe
    -0.48
    ategory
    -0.47
    ousel
    -0.47
    okane
    -0.46
    POSITIVE LOGITS
    Sax
    0.72
     Sax
    0.62
     Jude
    0.58
     Schwarz
    0.57
    ences
    0.53
    enced
    0.52
    ophone
    0.52
     Galile
    0.51
    encing
    0.50
    ãĥ¼ãĥ
    0.47
    Activations Density 0.182%

    No Known Activations