© 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. 40379
    Prev
    Next
    INDEX
    Explanations

    auto insurance-related terms and phrases

    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
    +0.20
    0.9%
    206
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.20
    0.09
    400
    +0.11
    0.08
    255
    +0.11
    0.10
    Negative Logits
    burgh
    -0.74
    ergic
    -0.72
     Notting
    -0.71
    soDeliveryDate
    -0.70
    ouf
    -0.68
     Cheong
    -0.67
     Depot
    -0.66
    phrine
    -0.66
    jay
    -0.66
    olate
    -0.65
    POSITIVE LOGITS
    tesy
    0.79
    ¿½
    0.74
     sus
    0.71
    ¥ŀ
    0.69
     solely
    0.69
    itiz
    0.68
     collabor
    0.68
     citiz
    0.68
     exclusively
    0.68
     servicing
    0.68
    Activations Density 9.342%

    No Known Activations