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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 744
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and players

    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
    373
    +0.09
    0.6%
    299
    +0.08
    0.5%
    730
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.09
    0.05
    373
    +0.08
    -0.02
    284
    +0.08
    0.04
    Negative Logits
     lifetime
    -0.54
     Cosponsors
    -0.54
    SPONSORED
    -0.53
    */(
    -0.48
     somew
    -0.48
    esson
    -0.47
    vernment
    -0.47
    abase
    -0.45
     favors
    -0.45
     DeL
    -0.45
    POSITIVE LOGITS
    oga
    0.60
    rim
    0.55
    ieri
    0.55
    iba
    0.51
    ras
    0.51
    uri
    0.50
    QUI
    0.50
    ghan
    0.49
    omon
    0.48
    ja
    0.48
    Activations Density 0.237%

    No Known Activations