© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14040
    Prev
    Next
    INDEX
    Explanations

    names, particularly those associated with various individuals

    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
    526
    +0.15
    0.5%
    659
    +0.15
    0.5%
    29
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.09
    288
    +0.15
    0.11
    313
    +0.15
    0.05
    Negative Logits
    ãĥ¼ãĥ³
    -1.16
    milo
    -1.08
     Peb
    -1.06
    BALL
    -1.02
     Flavoring
    -0.99
    hedon
    -0.97
    CRIP
    -0.97
    Interstitial
    -0.96
     Charm
    -0.96
    ilings
    -0.96
    POSITIVE LOGITS
    ette
    1.42
    etics
    1.30
    esis
    1.21
    nette
    1.19
     Francois
    1.14
    alog
    1.12
    ocide
    1.11
    ja
    1.11
     Baptist
    1.09
    bart
    1.08
    Activations Density 1.689%

    No Known Activations