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. 34642
    Prev
    Next
    INDEX
    Explanations

    examples related to sports events and competitions

    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
    566
    +0.13
    0.5%
    409
    +0.10
    0.4%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.13
    0.20
    762
    +0.10
    0.20
    55
    +0.09
    0.16
    Negative Logits
     mascul
    -0.73
     Nek
    -0.67
     Schiff
    -0.66
    Subject
    -0.66
     Kush
    -0.66
     neutron
    -0.64
     Pere
    -0.64
    Else
    -0.63
    )=(
    -0.62
     Linear
    -0.61
    POSITIVE LOGITS
     dearly
    0.94
     "$:/
    0.78
    borgh
    0.76
    illac
    0.75
     deems
    0.74
    abouts
    0.73
    ago
    0.73
    qt
    0.72
    ©¶æ¥µ
    0.72
     frequ
    0.71
    Activations Density 13.001%

    No Known Activations