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. 1630
    Prev
    Next
    INDEX
    Explanations

    economic terms and concepts

    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
    235
    +0.15
    0.7%
    288
    +0.13
    0.6%
    613
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.13
    235
    +0.13
    0.10
    575
    +0.12
    0.10
    Negative Logits
    holder
    -0.74
    holders
    -0.72
    fires
    -0.70
     Hancock
    -0.69
    worthy
    -0.67
     Veterans
    -0.66
     flyer
    -0.65
    urion
    -0.64
    Interstitial
    -0.64
     Delivery
    -0.63
    POSITIVE LOGITS
    icist
    1.23
    ophical
    1.19
    ology
    1.00
    ically
    1.00
     textbooks
    0.98
    hematic
    0.97
    odynamics
    0.94
    hemat
    0.92
     theory
    0.91
    ological
    0.89
    Activations Density 1.228%

    No Known Activations