© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    mentions of academic publishing and business practices in relation to institutions

    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
    447
    +0.24
    1.1%
    481
    +0.18
    0.8%
    92
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.24
    0.07
    439
    +0.18
    0.05
    288
    +0.12
    0.07
    Negative Logits
    aughs
    -0.72
    assis
    -0.63
    aye
    -0.56
    jah
    -0.55
    issan
    -0.54
    UCK
    -0.54
    phia
    -0.53
    ipes
    -0.53
    ttp
    -0.53
    keye
    -0.53
    POSITIVE LOGITS
     differently
    1.04
     solely
    0.90
     directly
    0.85
     exclusively
    0.83
    outside
    0.83
     purely
    0.83
     strictly
    0.82
     outside
    0.82
     containing
    0.80
     explicitly
    0.79
    Activations Density 0.433%

    No Known Activations