© 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 12288
    9. 8-RES_FS12288-JB
    11. 1770
    Prev
    Next
    INDEX
    Explanations

    mentions of penthouses

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    553
    +0.11
    0.5%
    99
    +0.11
    0.5%
    423
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    232
    +0.11
    0.03
    326
    +0.11
    0.03
    Negative Logits
    ãģĦ
    -0.99
    OAD
    -0.80
    士
    -0.65
    itism
    -0.64
     judgement
    -0.63
    istically
    -0.61
    culosis
    -0.61
     silence
    -0.61
    sts
    -0.61
    ãģį
    -0.60
    POSITIVE LOGITS
    raph
    1.14
    agon
    1.11
    agonal
    1.10
    agons
    0.96
    etr
    0.92
    acles
    0.90
    agram
    0.88
    hered
    0.87
    opus
    0.87
    rants
    0.87
    Activations Density 0.157%

    No Known Activations