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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 2710
    Prev
    Next
    INDEX
    Explanations

    human activities related to technology tools and protocols

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    407
    +0.12
    0.5%
    264
    +0.10
    0.5%
    206
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.07
    659
    +0.10
    0.07
    81
    +0.10
    0.06
    Negative Logits
     Barney
    -0.81
     Lor
    -0.73
    ande
    -0.73
     Bram
    -0.72
     HAR
    -0.72
     Fairfax
    -0.70
     Carroll
    -0.68
     Frederick
    -0.67
     Editors
    -0.66
     Colleg
    -0.66
    POSITIVE LOGITS
    0
    1.01
    º
    0.93
    sv
    0.88
    apo
    0.85
    id
    0.83
    ãĥĺãĥ©
    0.82
    α
    0.81
    ãĥ´ãĤ¡
    0.79
    itives
    0.79
    px
    0.79
    Activations Density 1.174%

    No Known Activations