© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 2246
    Prev
    Next
    INDEX
    Explanations

    references to government agencies, particularly the CIA

    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
    200
    +0.16
    0.7%
    288
    +0.12
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    200
    +0.16
    0.03
    239
    +0.12
    0.02
    682
    +0.12
    0.02
    Negative Logits
    ths
    -0.73
    kj
    -0.73
    ï¸
    -0.72
    kees
    -0.70
    amaz
    -0.70
    odic
    -0.69
     Mulcair
    -0.69
     Leafs
    -0.69
    own
    -0.69
    alist
    -0.68
    POSITIVE LOGITS
     annex
    1.01
     operatives
    0.90
    andestine
    0.84
     Headquarters
    0.84
     counterterrorism
    0.83
     covert
    0.82
     Director
    0.81
     operative
    0.81
     headquarters
    0.79
    CIA
    0.79
    Activations Density 0.020%

    No Known Activations