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. 34139
    Prev
    Next
    INDEX
    Explanations

    keywords related to political challenges or confrontations

    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
    +0.23
    1.1%
    71
    +0.11
    0.5%
    281
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.23
    0.17
    608
    +0.11
    0.21
    393
    +0.11
    0.27
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.73
    abet
    -0.73
    emetery
    -0.72
    oiler
    -0.71
    ophe
    -0.70
    fare
    -0.70
    ahon
    -0.69
    annabin
    -0.68
    \\\\
    -0.67
    ãĥı
    -0.66
    POSITIVE LOGITS
     questioning
    0.76
     authenticity
    0.73
     him
    0.73
     disbelief
    0.71
     contradictions
    0.70
     incumb
    0.69
     precon
    0.68
     unfl
    0.68
     questions
    0.68
    ibly
    0.67
    Activations Density 13.405%

    No Known Activations