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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 1823
    Prev
    Next
    INDEX
    Explanations

    phrases related to football player evaluations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    603
    +0.10
    0.4%
    668
    +0.09
    0.4%
    60
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    668
    +0.10
    0.07
    603
    +0.09
    0.07
    86
    +0.09
    0.07
    Negative Logits
     Capitalism
    -0.77
     cens
    -0.74
     censorship
    -0.72
     publishing
    -0.71
     Participants
    -0.70
    ictionary
    -0.70
     Publication
    -0.70
     Publishing
    -0.70
     override
    -0.69
    sth
    -0.69
    POSITIVE LOGITS
     versatility
    1.20
     rookie
    1.18
     underrated
    1.18
     teammates
    1.16
     teammate
    1.14
     athlet
    1.14
     athleticism
    1.14
     Rookie
    1.12
     standout
    1.12
     matchup
    1.09
    Activations Density 1.671%

    No Known Activations