© 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. 40333
    Prev
    Next
    INDEX
    Explanations

    information related to sports news and player profiles

    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
    659
    +0.09
    0.6%
    711
    +0.08
    0.5%
    335
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.14
    232
    +0.08
    0.08
    111
    +0.07
    0.08
    Negative Logits
     segreg
    -0.48
     artif
    -0.47
     scrut
    -0.45
     predec
    -0.45
     cov
    -0.44
    tight
    -0.44
    lance
    -0.43
    pection
    -0.43
    sylv
    -0.43
     proport
    -0.42
    POSITIVE LOGITS
    ĪĴ
    0.56
     Rowling
    0.53
    nik
    0.52
     Styles
    0.48
    zyk
    0.47
    ansen
    0.46
    eday
    0.46
    enne
    0.45
    iets
    0.45
    ESE
    0.45
    Activations Density 5.790%

    No Known Activations