© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 26592
    Prev
    Next
    INDEX
    Explanations

    words associated with responsibility or accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    112
    +0.11
    0.5%
    575
    +0.09
    0.4%
    706
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    112
    +0.11
    0.02
    733
    +0.09
    0.01
    682
    +0.09
    0.01
    Negative Logits
    matically
    -0.66
    aneers
    -0.63
     Cruiser
    -0.63
    swick
    -0.62
     CMS
    -0.62
    glers
    -0.61
    \\\\\\\\
    -0.60
    sonian
    -0.60
     pound
    -0.59
     Springs
    -0.59
    POSITIVE LOGITS
    olve
    1.36
    olutions
    1.35
    earcher
    1.32
    ervation
    1.31
    olved
    1.29
    olver
    1.27
    olves
    1.25
    idency
    1.23
    erves
    1.22
    urrection
    1.20
    Activations Density 0.005%

    No Known Activations