© 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. 19492
    Prev
    Next
    INDEX
    Explanations

    phrases related to offers and updates

    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
    +0.11
    0.5%
    480
    +0.10
    0.5%
    640
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.11
    0.01
    6
    +0.10
    0.03
    385
    +0.10
    0.03
    Negative Logits
     glac
    -0.73
     virginity
    -0.72
     manif
    -0.71
     exerc
    -0.69
    agall
    -0.69
     appropri
    -0.67
     wholes
    -0.66
     symp
    -0.66
     pellets
    -0.64
     manners
    -0.64
    POSITIVE LOGITS
    -+-+-+-+
    0.95
    Previous
    0.94
    MORE
    0.92
    Correction
    0.91
     Advertisement
    0.91
     SHARES
    0.89
    Original
    0.88
    Update
    0.85
    Plot
    0.84
     Previous
    0.83
    Activations Density 0.064%

    No Known Activations