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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 10236
    Prev
    Next
    INDEX
    Explanations

    text related to VR therapy, PTSD treatment, and potential medical applications of technology

    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
    447
    +0.24
    1.2%
    481
    +0.23
    1.2%
    228
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.24
    0.10
    705
    +0.23
    0.07
    608
    +0.10
    0.10
    Negative Logits
    osph
    -0.57
    issa
    -0.57
     pictured
    -0.56
    alde
    -0.55
    aucas
    -0.54
    abul
    -0.53
    uli
    -0.52
    ospital
    -0.52
    apest
    -0.51
    rete
    -0.51
    POSITIVE LOGITS
    etheless
    0.89
     reconsider
    0.78
     nonetheless
    0.74
     nostalgia
    0.71
     caution
    0.68
     downright
    0.67
     revis
    0.67
     recons
    0.67
     bullish
    0.65
     rethink
    0.64
    Activations Density 2.103%

    No Known Activations