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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8360
    Prev
    Next
    INDEX
    Explanations

    mentions of universities and research institutions

    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
    23
    +0.10
    0.5%
    424
    +0.10
    0.5%
    46
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.10
    0.03
    730
    +0.10
    0.03
    65
    +0.10
    0.03
    Negative Logits
    ãĤ¯
    -0.85
    ãĥ©
    -0.72
    venge
    -0.71
    yip
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.69
    rieg
    -0.67
    plet
    -0.67
    é»Ĵ
    -0.65
     clauses
    -0.65
    ynasty
    -0.64
    POSITIVE LOGITS
     Libraries
    1.02
     Faculty
    1.00
     School
    0.97
     Extension
    0.96
     faculty
    0.90
     campus
    0.87
     Teaching
    0.86
     Graduate
    0.86
     undergraduate
    0.85
     Robotics
    0.85
    Activations Density 0.061%

    No Known Activations