© 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. 17314
    Prev
    Next
    INDEX
    Explanations

    references to plants, farming activities, and related medical conditions

    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
    +0.55
    3.0%
    481
    +0.13
    0.7%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.55
    0.02
    266
    +0.13
    0.08
    288
    +0.13
    0.09
    Negative Logits
    azard
    -0.50
    yond
    -0.50
    senal
    -0.50
    ãĥª
    -0.48
    farious
    -0.48
    اÙĦ
    -0.47
     disadvant
    -0.47
     Guant
    -0.47
    Calling
    -0.47
    ãģĻ
    -0.46
    POSITIVE LOGITS
     meanwhile
    0.92
     consists
    0.89
     however
    0.89
     consisted
    0.83
     is
    0.82
     may
    0.81
     also
    0.81
     has
    0.81
     cannot
    0.80
     retains
    0.78
    Activations Density 0.836%

    No Known Activations