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

    Neuronpedia

    Jacobian LensNEW
    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. 8927
    Prev
    Next
    INDEX
    Explanations

    technical terms related to information technology and networks

    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
    139
    +0.12
    0.5%
    307
    +0.10
    0.5%
    374
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.12
    0.05
    45
    +0.10
    0.03
    399
    +0.09
    0.03
    Negative Logits
    atal
    -0.69
     Sahara
    -0.68
     Explosion
    -0.67
    abi
    -0.66
     Malays
    -0.63
    ODY
    -0.63
    emen
    -0.62
    onica
    -0.62
    mination
    -0.61
    ANC
    -0.60
    POSITIVE LOGITS
    etc
    1.05
     etc
    0.91
     deploy
    0.90
     engage
    0.88
     uphold
    0.87
     distribute
    0.86
     circulate
    0.85
     contribute
    0.83
     cultivate
    0.83
     declare
    0.82
    Activations Density 0.280%

    No Known Activations