© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 1970
    Prev
    Next
    INDEX
    Explanations

    numbers followed by descriptors or titles, possibly related to series, events, or creative works

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    480
    +0.53
    2.8%
    481
    +0.12
    0.6%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.53
    0.08
    480
    +0.12
    0.01
    266
    +0.11
    0.06
    Negative Logits
     customary
    -0.67
     outset
    -0.64
     tert
    -0.62
     combination
    -0.61
    umerous
    -0.61
     specially
    -0.60
     mechanically
    -0.60
     consecut
    -0.60
     ordinarily
    -0.60
     condemnation
    -0.58
    POSITIVE LOGITS
     Secrets
    0.99
     Bastard
    0.92
     Lives
    0.90
     Dreams
    0.89
     Adventures
    0.88
     Files
    0.88
     Memories
    0.87
     Voices
    0.86
     Tomorrow
    0.85
     Madness
    0.85
    Activations Density 0.536%

    No Known Activations