© 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. 13729
    Prev
    Next
    INDEX
    Explanations

    terms related to citations and references in a text

    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
    +0.29
    1.3%
    195
    +0.12
    0.5%
    554
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.29
    0.34
    385
    +0.12
    0.19
    608
    +0.12
    0.22
    Negative Logits
    orld
    -0.82
    ipeg
    -0.80
    amination
    -0.71
    vic
    -0.69
    quer
    -0.67
    visors
    -0.67
    heric
    -0.66
    hattan
    -0.65
    ifix
    -0.65
    ascript
    -0.64
    POSITIVE LOGITS
     warnings
    0.84
     citations
    0.81
     scriptures
    0.74
     examples
    0.74
     sources
    0.70
     excuses
    0.69
     unnamed
    0.68
     quotes
    0.68
     phrases
    0.65
     aloud
    0.64
    Activations Density 16.402%

    No Known Activations