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. 34150
    Prev
    Next
    INDEX
    Explanations

    phrases expressing tense or emotions in a dramatic or narrative context

    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
    +0.15
    0.8%
    449
    +0.09
    0.5%
    352
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    661
    +0.15
    0.08
    727
    +0.09
    0.09
    739
    +0.08
    0.05
    Negative Logits
    conservancy
    -0.60
    clus
    -0.59
     NCT
    -0.55
    æ©
    -0.54
     helicop
    -0.54
     TVs
    -0.54
    externalActionCode
    -0.53
    hower
    -0.53
     CT
    -0.53
     typ
    -0.52
    POSITIVE LOGITS
    -"
    0.86
    â̦"
    0.75
    raid
    0.72
    !?"
    0.71
    —"
    0.67
    fine
    0.66
    ãĢı
    0.65
    â̦."
    0.62
    stop
    0.61
    ..."
    0.60
    Activations Density 14.806%

    No Known Activations