© 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 49152
    9. 8-RES_FS49152-JB
    11. 26712
    Prev
    Next
    INDEX
    Explanations

    terms related to insect larvae and their impacts

    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
    549
    +0.12
    0.6%
    742
    +0.11
    0.5%
    659
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    232
    +0.11
    0.01
    419
    +0.11
    0.01
    Negative Logits
    ãģ®éŃĶ
    -0.94
    manship
    -0.93
    CRIP
    -0.91
    éĹĺ
    -0.79
    士
    -0.72
    代
    -0.71
    ĨĴ
    -0.68
    EEK
    -0.67
    ħĭ
    -0.67
    ãģį
    -0.67
    POSITIVE LOGITS
    vae
    1.04
    acy
    1.01
    issa
    0.98
    imore
    0.94
    abee
    0.94
    ousse
    0.93
    amo
    0.92
    acial
    0.90
    ocious
    0.90
    amar
    0.90
    Activations Density 0.005%

    No Known Activations