© 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. 9718
    Prev
    Next
    INDEX
    Explanations

    food-related terms, especially related to sausage and cooking techniques

    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
    726
    +0.09
    0.4%
    756
    +0.08
    0.4%
    465
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.02
    299
    +0.08
    0.02
    406
    +0.08
    0.02
    Negative Logits
    atform
    -0.86
    ADRA
    -0.81
     Circus
    -0.65
    imens
    -0.59
     arrang
    -0.59
    abase
    -0.56
    ADVERTISEMENT
    -0.56
    quarters
    -0.55
     Correspond
    -0.54
     CFR
    -0.54
    POSITIVE LOGITS
    oin
    0.81
    eki
    0.79
    amon
    0.75
    ignty
    0.74
    uku
    0.73
    aman
    0.69
    ÃŃa
    0.69
    din
    0.68
    orius
    0.67
    inia
    0.65
    Activations Density 0.052%

    No Known Activations