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 3072
    5. 8-RES_FS3072-JB
    6. 1452
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    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
    481
    +0.19
    0.9%
    430
    +0.11
    0.5%
    689
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.19
    0.13
    306
    +0.11
    0.11
    460
    +0.11
    0.10
    Negative Logits
    cro
    -0.66
    edIn
    -0.65
    adena
    -0.59
     Moons
    -0.59
     Desk
    -0.55
    guyen
    -0.54
    pires
    -0.54
     modular
    -0.53
    ezvous
    -0.53
     fict
    -0.53
    POSITIVE LOGITS
     onwards
    0.84
     attRot
    0.78
    Footnote
    0.76
    -'
    0.72
     due
    0.70
    frames
    0.70
     owing
    0.69
     onward
    0.69
     averaging
    0.68
    .
    0.66
    Activations Density 1.115%

    No Known Activations