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. 2712
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical positions and outcomes

    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
    635
    +0.10
    0.4%
    292
    +0.10
    0.4%
    699
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    727
    +0.10
    0.04
    206
    +0.10
    0.03
    566
    +0.09
    0.04
    Negative Logits
     indication
    -0.67
    heed
    -0.64
    lain
    -0.64
     intention
    -0.61
     contingency
    -0.61
    ongyang
    -0.61
     assurance
    -0.61
    grass
    -0.61
     Awareness
    -0.60
     suggestion
    -0.60
    POSITIVE LOGITS
    èª
    0.84
    ãĥĩãĤ£
    0.84
     needing
    0.81
     deleting
    0.78
     liking
    0.77
     owning
    0.77
     accidentally
    0.76
    missing
    0.76
     encountering
    0.75
     trapped
    0.74
    Activations Density 0.693%

    No Known Activations