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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45241
    Prev
    Next
    INDEX
    Explanations

    information related to a specific person named Manning, potentially focusing on legal proceedings and public scrutiny

    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
    +0.15
    0.8%
    99
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.17
    326
    +0.15
    0.16
    99
    +0.11
    0.08
    Negative Logits
    ork
    -0.67
    hips
    -0.67
    âĸ¬âĸ¬
    -0.64
    chrom
    -0.63
    akespe
    -0.63
    relation
    -0.63
    urnal
    -0.62
     Debor
    -0.62
    ayne
    -0.61
    ideon
    -0.61
    POSITIVE LOGITS
     Manning
    1.06
    ufact
    0.94
    hattan
    0.68
     Broncos
    0.68
     Passing
    0.67
    IUM
    0.67
    lete
    0.66
    ifest
    0.65
    ham
    0.61
    mberg
    0.59
    Activations Density 5.113%

    No Known Activations