© 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 24576
    9. 8-RES_FS24576-JB
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by a word denoting a physical location

    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
    759
    +0.11
    0.5%
    364
    +0.10
    0.5%
    728
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    750
    +0.11
    0.02
    654
    +0.10
    0.02
    759
    +0.10
    0.02
    Negative Logits
    TOP
    -0.78
    Skill
    -0.62
    oÄŁ
    -0.61
    theless
    -0.60
    Chel
    -0.60
    eros
    -0.59
    EStreamFrame
    -0.58
    Requ
    -0.57
    accompan
    -0.56
    BER
    -0.56
    POSITIVE LOGITS
    scope
    0.83
    glass
    0.82
     afar
    0.77
     favorably
    0.76
    oscope
    0.76
    river
    0.72
     microscope
    0.71
     vain
    0.71
     lens
    0.71
     Compass
    0.70
    Activations Density 0.087%

    No Known Activations