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

    Neuronpedia

    Jacobian LensNEW
    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. 6101
    Prev
    Next
    INDEX
    Explanations

    references to time and events happening in a sequence

    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
    293
    +0.11
    0.5%
    598
    +0.11
    0.5%
    210
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.11
    0.03
    566
    +0.11
    0.03
    598
    +0.10
    0.02
    Negative Logits
     suggestion
    -0.74
     ransom
    -0.69
    bol
    -0.69
     strives
    -0.66
     intimid
    -0.62
     ambush
    -0.62
     hinder
    -0.61
     interchange
    -0.61
     investigates
    -0.60
     uses
    -0.60
    POSITIVE LOGITS
    ©¶æ¥µ
    0.85
     exhausted
    0.85
    apsed
    0.80
     already
    0.78
    enough
    0.76
    uberty
    0.76
    ÃįÃį
    0.73
     gone
    0.72
     unmist
    0.71
     surpassed
    0.71
    Activations Density 0.236%

    No Known Activations