Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 45912
    Prev
    Next
    INDEX
    Explanations

    information related to political elections, candidates, and voting processes

    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
    +0.21
    1.1%
    183
    +0.12
    0.6%
    243
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.21
    0.21
    385
    +0.12
    0.16
    362
    +0.08
    0.12
    Negative Logits
    uras
    -0.63
    Factor
    -0.59
     deprecated
    -0.57
    IDER
    -0.56
    Root
    -0.54
    Redd
    -0.52
     Redd
    -0.51
    gur
    -0.50
    TAG
    -0.49
     hunger
    -0.49
    POSITIVE LOGITS
    election
    0.84
     reelection
    0.78
    elect
    0.74
     majorities
    0.72
     electoral
    0.66
     elector
    0.65
     landslide
    0.65
     elections
    0.63
     primaries
    0.63
     306
    0.61
    Activations Density 10.902%

    No Known Activations