© 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. 45987
    Prev
    Next
    INDEX
    Explanations

    mentions of education, charter schools, and related terms

    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
    288
    +0.16
    0.9%
    447
    +0.13
    0.7%
    302
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    302
    +0.16
    0.10
    52
    +0.13
    0.06
    288
    +0.10
    0.17
    Negative Logits
    ocate
    -0.60
    Downloadha
    -0.60
    ugs
    -0.60
    utenberg
    -0.59
    Lenin
    -0.58
    nesota
    -0.58
    ewski
    -0.58
    pez
    -0.57
    encer
    -0.57
     Rove
    -0.55
    POSITIVE LOGITS
    icut
    0.72
     charter
    0.61
     renewal
    0.58
     Charter
    0.56
    fman
    0.56
    zeb
    0.54
    holder
    0.53
    zman
    0.52
    iffs
    0.52
     schools
    0.52
    Activations Density 6.753%

    No Known Activations