© 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. 7904
    Prev
    Next
    INDEX
    Explanations

    mentions of assistance or aid in various contexts, including police investigations, medical missions, and collaborative work with robots

    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
    679
    +0.16
    0.7%
    253
    +0.14
    0.6%
    458
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.16
    0.02
    679
    +0.14
    0.02
    458
    +0.09
    0.02
    Negative Logits
    place
    -0.78
    bon
    -0.67
    ban
    -0.66
    puted
    -0.65
    ndra
    -0.64
    bara
    -0.64
    meat
    -0.64
    odus
    -0.64
    boys
    -0.62
    nu
    -0.62
    POSITIVE LOGITS
     assisting
    0.78
     assistance
    0.71
     assist
    0.71
     Desk
    0.69
     guiActiveUn
    0.68
     aid
    0.67
     guiIcon
    0.67
     aiding
    0.65
    atively
    0.64
     facilitate
    0.64
    Activations Density 0.040%

    No Known Activations