© 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 EvalsExportsinterp-engineNEWAPI 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. 4954
    Prev
    Next
    INDEX
    Explanations

    names or terms related to conflicts and controversies

    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
    737
    +0.11
    0.5%
    616
    +0.10
    0.5%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.11
    0.03
    406
    +0.10
    0.03
    738
    +0.09
    0.02
    Negative Logits
    rency
    -0.84
    ãĥ¼ãĥĨ
    -0.82
    enment
    -0.72
    rawdownloadcloneembedreportprint
    -0.64
    ãĥĥãĥĪ
    -0.60
     Collider
    -0.60
    fitting
    -0.60
    BILITIES
    -0.59
    ctive
    -0.57
    ãĥŃ
    -0.57
    POSITIVE LOGITS
    oslav
    1.00
    ovych
    0.88
    abytes
    0.82
    akov
    0.82
    kees
    0.77
    ikh
    0.74
    oub
    0.68
    abyte
    0.67
    bye
    0.67
    ouk
    0.66
    Activations Density 0.081%

    No Known Activations