© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 1543
    Prev
    Next
    INDEX
    Explanations

    information related to events, conferences, and listings

    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
    370
    +0.10
    0.5%
    630
    +0.09
    0.4%
    679
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.08
    370
    +0.09
    0.04
    229
    +0.09
    0.04
    Negative Logits
    dayName
    -0.58
     sew
    -0.58
     somehow
    -0.57
    ARS
    -0.57
     eq
    -0.56
    otiation
    -0.56
     damned
    -0.56
    rome
    -0.55
    enser
    -0.55
    Untitled
    -0.55
    POSITIVE LOGITS
     include
    1.63
    :-
    1.32
    *:
    1.24
     Include
    1.22
     included
    1.12
    include
    1.12
    %:
    1.11
    :
    1.10
     includes
    1.10
     Included
    1.04
    Activations Density 0.821%

    No Known Activations