© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 3986
    Prev
    Next
    INDEX
    Explanations

    names and titles related to politics and entertainment personalities

    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
    679
    +0.09
    0.4%
    343
    +0.09
    0.4%
    587
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.21
    343
    +0.09
    0.10
    346
    +0.09
    0.10
    Negative Logits
    EEK
    -0.70
    Brave
    -0.69
    rium
    -0.67
    PsyNetMessage
    -0.66
    essional
    -0.66
     Independence
    -0.66
    natureconservancy
    -0.63
    OHN
    -0.63
    ASE
    -0.61
    bery
    -0.61
    POSITIVE LOGITS
     Duterte
    0.79
    uterte
    0.72
    /**
    0.65
     contag
    0.64
     Jinping
    0.63
     injected
    0.63
    eln
    0.62
     imperson
    0.60
     unleashed
    0.60
    ascus
    0.58
    Activations Density 5.912%

    No Known Activations