© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    character names in news articles

    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
    480
    +0.49
    2.6%
    481
    +0.17
    0.9%
    659
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.49
    0.10
    700
    +0.17
    0.08
    232
    +0.13
    0.07
    Negative Logits
     ambassadors
    -0.58
     apex
    -0.54
     nonexistent
    -0.54
     repressive
    -0.53
    ModLoader
    -0.53
     tourism
    -0.52
     loopholes
    -0.52
     envy
    -0.51
     patronage
    -0.51
     ultras
    -0.51
    POSITIVE LOGITS
    owski
    1.08
    ansky
    1.04
    itsch
    1.04
    baum
    1.03
    oglu
    1.02
    opoulos
    1.02
    berger
    1.00
    icz
    0.98
    iewicz
    0.98
    chuk
    0.97
    Activations Density 0.308%

    No Known Activations