© 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 49152
    5. 8-RES_FS49152-JB
    6. 37462
    Prev
    Next
    INDEX
    Explanations

    references to specific dates or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    640
    +0.11
    0.5%
    471
    +0.10
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.11
    0.04
    509
    +0.10
    0.04
    764
    +0.10
    0.04
    Negative Logits
    MODE
    -0.71
     cruc
    -0.71
    peat
    -0.62
     choke
    -0.62
    RL
    -0.60
    $$
    -0.60
    ennes
    -0.59
    amus
    -0.59
    riages
    -0.57
    harm
    -0.56
    POSITIVE LOGITS
    slaught
    1.23
     behalf
    1.22
    coming
    1.09
    look
    1.07
    etime
    1.03
     July
    1.02
     Wednesday
    1.02
     occasion
    1.02
     September
    1.01
     Thursday
    1.01
    Activations Density 0.041%

    No Known Activations