© 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. 2364
    Prev
    Next
    INDEX
    Explanations

    locations or dates within a sentence

    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
    373
    +0.24
    1.1%
    481
    +0.16
    0.8%
    129
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    582
    +0.24
    0.03
    471
    +0.16
    0.03
    373
    +0.10
    -0.03
    Negative Logits
    vantage
    -0.77
    ombat
    -0.68
    elly
    -0.68
    :#
    -0.63
    ogether
    -0.63
    .:
    -0.62
    anon
    -0.62
    uckland
    -0.59
    .#
    -0.59
    .""
    -0.58
    POSITIVE LOGITS
    accompanied
    0.62
     nineteen
    0.60
     consultation
    0.60
     waning
    0.58
     reviewing
    0.57
     announcing
    0.57
     commem
    0.56
    elfth
    0.56
    lication
    0.56
     Improvement
    0.55
    Activations Density 0.271%

    No Known Activations