© 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. 300
    Prev
    Next
    INDEX
    Explanations

    mentions of locations related to drug-related issues

    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
    373
    +0.13
    0.6%
    737
    +0.10
    0.5%
    234
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.01
    234
    +0.10
    0.01
    470
    +0.10
    0.01
    Negative Logits
    fin
    -0.67
    chall
    -0.67
    etts
    -0.64
    stellar
    -0.63
    naire
    -0.61
    laus
    -0.61
     barg
    -0.61
    hetically
    -0.61
    cellence
    -0.59
    past
    -0.59
    POSITIVE LOGITS
    PLIED
    0.73
     DRM
    0.68
    taboola
    0.66
     Ùħ
    0.64
     device
    0.62
     Enable
    0.61
     Ø
    0.61
     devices
    0.61
     iTunes
    0.61
    --------------------------------------------------------
    0.60
    Activations Density 0.014%

    No Known Activations