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

    Neuronpedia

    APICircuit 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. 13454
    Prev
    Next
    INDEX
    Explanations

    statistics and performance metrics in sports contexts

    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
    188
    +0.12
    0.6%
    447
    +0.10
    0.6%
    285
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.12
    0.09
    188
    +0.10
    0.09
    540
    +0.10
    0.16
    Negative Logits
    opol
    -0.62
    bus
    -0.57
    tube
    -0.54
    Asia
    -0.53
     Horizons
    -0.53
    eday
    -0.53
     recess
    -0.52
    zhou
    -0.52
     Transport
    -0.52
    AFTA
    -0.52
    POSITIVE LOGITS
     (.
    0.78
    BIP
    0.75
     offensively
    0.72
     coefficient
    0.71
    orsi
    0.70
     fastball
    0.67
    adjusted
    0.66
    iveness
    0.65
     squared
    0.65
     ratio
    0.65
    Activations Density 10.733%

    No Known Activations