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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 37313
    Prev
    Next
    INDEX
    Explanations

    technical terms related to science and engineering

    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
    481
    +0.13
    0.6%
    271
    +0.10
    0.5%
    362
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.13
    0.01
    288
    +0.10
    0.02
    404
    +0.10
    0.02
    Negative Logits
    emark
    -0.96
    MAS
    -0.90
    nah
    -0.87
    Ãį
    -0.86
    bourg
    -0.86
    ouf
    -0.86
    #$#$
    -0.84
    Ey
    -0.82
    NR
    -0.82
    Corp
    -0.82
    POSITIVE LOGITS
     traject
    1.01
     warfare
    1.00
     transmission
    0.98
     environments
    0.97
     imaging
    0.97
     propulsion
    0.96
     confinement
    0.95
     transmissions
    0.94
    heric
    0.93
     travel
    0.92
    Activations Density 0.043%

    No Known Activations