© 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 24576
    9. 8-RES_FS24576-JB
    11. 1605
    Prev
    Next
    INDEX
    Explanations

    numeric ranges related to quantities or values

    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
    724
    +0.15
    0.7%
    260
    +0.10
    0.5%
    655
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.15
    0.07
    655
    +0.10
    0.06
    260
    +0.10
    0.06
    Negative Logits
     Definition
    -0.65
    agate
    -0.62
     Dynamics
    -0.60
     resolves
    -0.59
     cath
    -0.56
     distur
    -0.56
     Puzzles
    -0.56
     relates
    -0.56
     Holiday
    -0.55
     directions
    -0.54
    POSITIVE LOGITS
     dozen
    1.14
    undreds
    1.14
    dozen
    1.01
     eighty
    0.88
     450
    0.86
    ousands
    0.84
     700
    0.83
     130
    0.82
     800
    0.82
     hundred
    0.82
    Activations Density 0.202%

    No Known Activations