© 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 3072
    9. 8-RES_FS3072-JB
    11. 230
    Prev
    Next
    INDEX
    Explanations

    legal terms and related 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_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    659
    +0.12
    0.5%
    509
    +0.12
    0.5%
    429
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.13
    314
    +0.12
    0.00
    176
    +0.10
    0.05
    Negative Logits
     pony
    -0.74
     Costco
    -0.68
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.65
     Cerberus
    -0.64
     Sno
    -0.64
     horse
    -0.64
     Disneyland
    -0.63
     Nirvana
    -0.63
     Hobbit
    -0.61
     Sochi
    -0.61
    POSITIVE LOGITS
    ifully
    1.28
    rarily
    1.19
    cially
    1.19
    ately
    1.13
    itionally
    1.13
    ogether
    1.12
    quartered
    1.10
    respective
    1.09
    cknowled
    1.08
    ometime
    1.07
    Activations Density 1.319%

    No Known Activations