© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 725
    Prev
    Next
    INDEX
    Explanations

    narratives of events unfolding in specific places

    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
    555
    +0.11
    0.5%
    20
    +0.10
    0.5%
    215
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.11
    -0.02
    762
    +0.10
    0.14
    374
    +0.10
    0.03
    Negative Logits
     Historically
    -0.78
     historically
    -0.78
     globally
    -0.74
    uably
    -0.73
     advocates
    -0.72
     achieves
    -0.72
     strives
    -0.72
    urches
    -0.71
     broadly
    -0.71
     disproportionately
    -0.70
    POSITIVE LOGITS
     supper
    0.84
     incrim
    0.80
     whereabouts
    0.79
     hers
    0.76
    Delivery
    0.74
     downstairs
    0.73
     tresp
    0.73
    —"
    0.73
     trespass
    0.72
     prank
    0.72
    Activations Density 4.294%

    No Known Activations