© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 9794
    Prev
    Next
    INDEX
    Explanations

    information related to sports and personal achievements

    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
    36
    +0.17
    0.8%
    393
    +0.13
    0.6%
    704
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.17
    0.08
    704
    +0.13
    0.04
    512
    +0.12
    0.04
    Negative Logits
    Edit
    -0.83
    edit
    -0.74
    Versions
    -0.70
     Ern
    -0.70
    events
    -0.68
    EDIT
    -0.67
     Denis
    -0.67
    achu
    -0.65
     Gloves
    -0.63
     Izan
    -0.63
    POSITIVE LOGITS
     fixture
    1.23
     thorn
    1.18
     staple
    1.17
     fruitful
    1.16
     cornerstone
    1.07
     catalyst
    0.99
     hallmark
    0.98
     boon
    0.97
     constant
    0.97
     steady
    0.97
    Activations Density 0.121%

    No Known Activations