© 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. 4365
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names, possibly associated with legal or judicial contexts

    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
    113
    +0.12
    0.5%
    40
    +0.10
    0.5%
    425
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.12
    0.07
    106
    +0.10
    0.07
    508
    +0.10
    0.06
    Negative Logits
    zees
    -0.74
     stockp
    -0.73
    alties
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
    avorite
    -0.71
     Malfoy
    -0.69
    inventory
    -0.69
     stockpile
    -0.67
    lyak
    -0.67
    aceae
    -0.67
    POSITIVE LOGITS
    News
    1.15
    Journal
    1.14
     News
    1.13
     Reporter
    1.12
     Daily
    1.12
     reporters
    1.09
     Tribune
    1.04
    aretz
    1.03
     Telegraph
    1.02
    Daily
    1.01
    Activations Density 0.735%

    No Known Activations