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. 19049
    Prev
    Next
    INDEX
    Explanations

    words related to waiting or anticipation

    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
    706
    +0.12
    0.6%
    343
    +0.11
    0.5%
    119
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.12
    0.02
    659
    +0.11
    0.02
    326
    +0.10
    0.01
    Negative Logits
    sis
    -0.83
    handedly
    -0.74
    xual
    -0.70
    rations
    -0.66
    displayText
    -0.65
    lycer
    -0.65
    rics
    -0.64
    erous
    -0.64
     Luther
    -0.64
    raph
    -0.62
    POSITIVE LOGITS
    velength
    1.60
    veland
    1.08
    isted
    1.01
    pload
    0.98
    iting
    0.95
    aii
    0.95
    heed
    0.93
    Wa
    0.92
    ibling
    0.92
    pless
    0.90
    Activations Density 0.023%

    No Known Activations