© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17840
    Prev
    Next
    INDEX
    Explanations

    information related to high schools and students

    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
    496
    +0.12
    0.5%
    640
    +0.11
    0.5%
    359
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.12
    0.02
    166
    +0.11
    0.02
    187
    +0.10
    0.02
    Negative Logits
    arium
    -0.84
    oidal
    -0.78
     rall
    -0.74
    vernment
    -0.74
    ĸļ
    -0.68
    女
    -0.67
    ious
    -0.66
    ophy
    -0.66
    OPLE
    -0.65
     pus
    -0.65
    POSITIVE LOGITS
    landers
    1.27
    lighting
    1.10
     School
    1.10
    school
    0.98
    lights
    0.97
    nesses
    0.93
    light
    0.93
    lander
    0.87
    croft
    0.85
    WAY
    0.85
    Activations Density 0.028%

    No Known Activations