© 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. 19434
    Prev
    Next
    INDEX
    Explanations

    technical terms related to technology and scientific experiments

    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
    481
    +0.18
    0.8%
    46
    +0.10
    0.5%
    513
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.09
    338
    +0.10
    0.05
    351
    +0.09
    0.04
    Negative Logits
    reetings
    -0.78
    iversary
    -0.70
    Islamic
    -0.69
    Cele
    -0.69
     Protector
    -0.69
     Particip
    -0.69
    Happy
    -0.69
    Allah
    -0.69
     Congratulations
    -0.69
    Congratulations
    -0.68
    POSITIVE LOGITS
     inability
    1.37
     unus
    1.28
     inefficient
    1.27
     unable
    1.26
     inexper
    1.19
     deteriorated
    1.18
     inexperienced
    1.17
     inadequate
    1.16
     hampered
    1.15
     unreliable
    1.15
    Activations Density 1.097%

    No Known Activations