© 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. 18528
    Prev
    Next
    INDEX
    Explanations

    phrases related to seeking or searching for something

    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
    383
    +0.16
    0.7%
    195
    +0.11
    0.5%
    361
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.16
    0.03
    184
    +0.11
    0.02
    646
    +0.10
    0.03
    Negative Logits
    rome
    -0.73
    heartedly
    -0.72
    raid
    -0.69
    riks
    -0.68
    minus
    -0.66
    olor
    -0.66
     Loren
    -0.66
    amination
    -0.65
    oyal
    -0.64
    mson
    -0.64
    POSITIVE LOGITS
     refuge
    0.95
     clarification
    0.91
     revenge
    0.89
     answers
    0.85
     unsuccessfully
    0.84
     reimbursement
    0.82
     guidance
    0.81
     forgiveness
    0.81
     inspiration
    0.79
     redress
    0.78
    Activations Density 0.039%

    No Known Activations