© 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 Local
    9. 6-RES_SCL-AJT
    11. 33014
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical references, national identities, and current events in England

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.18
    0.8%
    527
    +0.12
    0.6%
    688
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.18
    0.06
    288
    +0.12
    0.13
    527
    +0.10
    0.02
    Negative Logits
    henko
    -0.78
    yout
    -0.77
    onday
    -0.76
    ĸļ
    -0.74
    asta
    -0.74
    etsk
    -0.74
    PsyNetMessage
    -0.74
    onym
    -0.73
    dq
    -0.70
    heny
    -0.70
    POSITIVE LOGITS
    shire
    0.95
     Yard
    0.81
    ury
    0.77
     Crown
    0.77
    bridge
    0.76
     Spit
    0.75
     Literature
    0.73
     Volunteers
    0.69
     Defence
    0.68
     Rugby
    0.66
    Activations Density 4.667%

    No Known Activations