© 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 12288
    9. 8-RES_FS12288-JB
    11. 471
    Prev
    Next
    INDEX
    Explanations

    questions expressing confusion or seeking reasons behind 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    57
    +0.11
    0.5%
    594
    +0.10
    0.5%
    750
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.11
    0.04
    594
    +0.10
    0.04
    533
    +0.10
    0.04
    Negative Logits
     Roller
    -0.71
    interstitial
    -0.69
    iece
    -0.68
    izen
    -0.68
    ymph
    -0.64
    iHUD
    -0.62
    operation
    -0.59
    Laughs
    -0.59
    lator
    -0.59
    pocket
    -0.58
    POSITIVE LOGITS
     bother
    1.00
    soever
    0.99
    ?
    0.84
    brow
    0.77
    ?".
    0.75
    ?'
    0.75
    !?
    0.74
    why
    0.74
     Does
    0.73
    ?!
    0.73
    Activations Density 0.045%

    No Known Activations