© 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. 34772
    Prev
    Next
    INDEX
    Explanations

    phrases related to software development, project updates, and user engagement

    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
    461
    +0.11
    0.5%
    393
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.11
    0.21
    269
    +0.10
    0.08
    49
    +0.10
    0.12
    Negative Logits
    ACP
    -0.81
    inction
    -0.78
    OPE
    -0.74
    ipal
    -0.73
    emon
    -0.72
    ingu
    -0.71
    eca
    -0.70
    umbling
    -0.69
    inct
    -0.69
    ģ«
    -0.68
    POSITIVE LOGITS
     guys
    1.19
    tub
    1.01
    're
    0.93
     yourselves
    0.92
     mileage
    0.88
     gentlemen
    0.80
    RS
    0.80
     majesty
    0.79
     kindly
    0.78
    STON
    0.73
    Activations Density 7.921%

    No Known Activations