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. 34387
    Prev
    Next
    INDEX
    Explanations

    information related to weightlifting and physical training routines

    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
    763
    +0.12
    0.6%
    447
    +0.10
    0.5%
    56
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.27
    373
    +0.10
    -0.22
    659
    +0.09
    0.12
    Negative Logits
     .)
    -0.69
    SPONSORED
    -0.66
     ."
    -0.61
    .''
    -0.60
     ''
    -0.60
    hran
    -0.56
     disturbed
    -0.55
    .�
    -0.54
    Âł
    -0.54
     disapp
    -0.54
    POSITIVE LOGITS
     Profile
    0.94
     âĵĺ
    0.84
    ':
    0.77
    %:
    0.75
     ::
    0.67
    ":{"
    0.66
    "]=>
    0.64
    \":
    0.64
    *:
    0.64
     Problems
    0.63
    Activations Density 12.827%

    No Known Activations