© 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. 12377
    Prev
    Next
    INDEX
    Explanations

    words related to historical events, research, and discoveries

    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
    761
    +0.12
    0.6%
    581
    +0.09
    0.4%
    153
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.12
    0.03
    26
    +0.09
    0.02
    371
    +0.09
    0.02
    Negative Logits
    ngth
    -0.83
    ihar
    -0.78
    aternal
    -0.61
    agging
    -0.59
    hooting
    -0.59
    pering
    -0.59
     forgiven
    -0.58
    idity
    -0.58
     chasing
    -0.58
    pora
    -0.57
    POSITIVE LOGITS
    tons
    1.49
    ham
    1.28
    HAM
    1.17
    ton
    1.10
    redients
    1.09
    uez
    1.04
    ame
    0.91
    haus
    0.90
    lass
    0.88
    hoff
    0.88
    Activations Density 0.062%

    No Known Activations