© 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. 19553
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations being considered as potential targets for particular actions

    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
    608
    +0.17
    0.8%
    620
    +0.12
    0.5%
    549
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.17
    0.06
    620
    +0.12
    0.03
    403
    +0.10
    0.03
    Negative Logits
    daq
    -0.74
    stan
    -0.72
    boy
    -0.70
    loo
    -0.70
    nick
    -0.69
    CV
    -0.68
    beat
    -0.68
    edin
    -0.67
    book
    -0.66
    wa
    -0.66
    POSITIVE LOGITS
    geries
    1.02
     beginners
    0.98
    bidden
    0.97
     determining
    0.96
     locating
    0.95
    gery
    0.93
     constructing
    0.93
     navigating
    0.92
     sorts
    0.90
     selecting
    0.89
    Activations Density 0.135%

    No Known Activations