© 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. 45992
    Prev
    Next
    INDEX
    Explanations

    terms related to legal matters, decision-making, competition, and power struggles

    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
    0.9%
    288
    +0.10
    0.5%
    195
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.17
    151
    +0.10
    0.13
    665
    +0.10
    0.11
    Negative Logits
    hedral
    -0.67
    bor
    -0.65
     stub
    -0.59
     wells
    -0.57
    por
    -0.57
    pointers
    -0.56
    uddy
    -0.56
    pora
    -0.56
    carbon
    -0.56
    pled
    -0.55
    POSITIVE LOGITS
     prevail
    0.93
    enance
    0.88
     prevailed
    0.84
    acebook
    0.78
    rences
    0.76
    ously
    0.72
     prev
    0.68
     against
    0.68
    theless
    0.66
    SHIP
    0.66
    Activations Density 5.059%

    No Known Activations