© 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 24576
    9. 8-RES_FS24576-JB
    11. 18831
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, decisions, and authoritative 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
    447
    +0.18
    0.8%
    724
    +0.11
    0.5%
    704
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.18
    0.04
    540
    +0.11
    0.04
    576
    +0.10
    0.02
    Negative Logits
     sling
    -0.72
     Tau
    -0.61
     Plate
    -0.60
     Launch
    -0.60
     booze
    -0.60
     Moose
    -0.60
    Scan
    -0.59
     Cure
    -0.59
     nutshell
    -0.58
     Lounge
    -0.57
    POSITIVE LOGITS
     existed
    0.99
     exists
    0.96
     exist
    0.87
    manship
    0.84
    idious
    0.81
    SHIP
    0.78
    hip
    0.72
    ieties
    0.70
    roman
    0.69
    itarian
    0.69
    Activations Density 0.144%

    No Known Activations