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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11731
    Prev
    Next
    INDEX
    Explanations

    phrases related to civic engagement and community involvement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    685
    +0.10
    0.5%
    470
    +0.10
    0.5%
    700
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.10
    0.04
    685
    +0.10
    0.03
    431
    +0.10
    0.03
    Negative Logits
    similar
    -0.70
    uthor
    -0.69
    ventions
    -0.67
    sequ
    -0.64
    juries
    -0.64
     similarly
    -0.62
    apons
    -0.62
    ikers
    -0.61
    artisan
    -0.61
    pox
    -0.61
    POSITIVE LOGITS
     nutshell
    0.70
     sorely
    0.67
    tin
    0.66
     longest
    0.65
     boils
    0.64
    liest
    0.64
     nightmares
    0.64
    AME
    0.63
    !.
    0.62
     Nare
    0.62
    Activations Density 0.232%

    No Known Activations