© 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. 1750
    Prev
    Next
    INDEX
    Explanations

    words related to coding and technical concepts

    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
    167
    +0.10
    0.5%
    232
    +0.10
    0.5%
    628
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.02
    57
    +0.10
    0.02
    85
    +0.10
    0.02
    Negative Logits
    PORT
    -0.90
    HAEL
    -0.80
    DragonMagazine
    -0.70
    UGC
    -0.68
     1886
    -0.67
    767
    -0.67
    stellar
    -0.67
    BuyableInstoreAndOnline
    -0.65
    phrine
    -0.65
    IENT
    -0.64
    POSITIVE LOGITS
    omever
    1.21
    inging
    1.17
    inges
    1.11
    ipper
    1.07
    ipp
    0.99
    idd
    0.98
    inged
    0.98
    ashing
    0.98
    ippers
    0.94
    irlf
    0.93
    Activations Density 0.019%

    No Known Activations