© 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. 11073
    Prev
    Next
    INDEX
    Explanations

    locations and details related to events and incidents

    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
    480
    +0.52
    2.8%
    87
    +0.12
    0.6%
    266
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.52
    0.11
    480
    +0.12
    0.02
    266
    +0.12
    0.08
    Negative Logits
    ificant
    -0.59
     looph
    -0.58
    theless
    -0.57
    ulative
    -0.54
    TPPStreamerBot
    -0.54
    ngth
    -0.53
     underestimated
    -0.50
    ailable
    -0.50
     anecd
    -0.49
     concise
    -0.48
    POSITIVE LOGITS
    abilia
    0.62
     fame
    0.59
     Belfast
    0.58
     plantations
    0.54
     persuasion
    0.52
     ranch
    0.52
     Pavilion
    0.51
     encamp
    0.51
     kios
    0.50
     pav
    0.50
    Activations Density 0.687%

    No Known Activations