© 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 24576
    9. 8-RES_FS24576-JB
    11. 19706
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific product or brand name

    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
    649
    +0.12
    0.5%
    526
    +0.10
    0.5%
    203
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    343
    +0.10
    0.01
    326
    +0.10
    0.01
    Negative Logits
     Faul
    -0.73
    ãĥ¼ãĥ³
    -0.71
     defic
    -0.70
    listed
    -0.70
    FUL
    -0.69
     Ago
    -0.67
    ously
    -0.67
     Lauder
    -0.64
    ãĤ¤ãĥĪ
    -0.64
     REPORT
    -0.63
    POSITIVE LOGITS
    esta
    1.28
    iatric
    1.20
    casters
    1.07
    iat
    1.01
    bean
    1.00
    caster
    0.99
    ols
    0.97
    asus
    0.95
    omatic
    0.83
    lov
    0.83
    Activations Density 0.015%

    No Known Activations