© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 1536
    9. 8-RES_FS1536-JB
    11. 1024
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and spatial positioning

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    288
    +0.11
    0.5%
    314
    +0.10
    0.5%
    710
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.14
    564
    +0.10
    0.09
    325
    +0.10
    0.09
    Negative Logits
     Suc
    -0.72
    volent
    -0.71
     Eps
    -0.70
     Flores
    -0.68
     Phi
    -0.64
     Mori
    -0.64
     Braz
    -0.62
     Tasman
    -0.61
     Strait
    -0.61
     Bers
    -0.61
    POSITIVE LOGITS
    locked
    1.21
    hog
    1.17
    plane
    1.10
    fare
    1.10
    raid
    1.10
    locks
    1.07
    waves
    1.05
    tight
    1.04
    scape
    1.03
    side
    1.02
    Activations Density 1.893%

    No Known Activations