© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibilities or obligations

    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
    285
    +0.12
    0.6%
    27
    +0.10
    0.4%
    658
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.12
    0.01
    225
    +0.10
    0.02
    34
    +0.09
    0.01
    Negative Logits
    naissance
    -0.74
     rave
    -0.71
    apeake
    -0.68
    confirmed
    -0.68
    riber
    -0.66
    wagen
    -0.66
     rall
    -0.64
    regor
    -0.64
    zsche
    -0.63
    orgetown
    -0.63
    POSITIVE LOGITS
     burden
    1.36
     burdens
    1.33
    ome
    0.98
     borne
    0.98
     burd
    0.98
     incurred
    0.94
     levied
    0.91
     imposed
    0.90
     inflicted
    0.83
     load
    0.82
    Activations Density 0.040%

    No Known Activations