© 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 49152
    9. 8-RES_FS49152-JB
    11. 45540
    Prev
    Next
    INDEX
    Explanations

    words related to the name 'SAVARKAR' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    481
    +0.19
    0.9%
    564
    +0.11
    0.5%
    418
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.19
    0.04
    232
    +0.11
    0.03
    579
    +0.10
    0.03
    Negative Logits
     skelet
    -0.85
     psychiat
    -0.71
     cryst
    -0.70
     abnorm
    -0.69
    axter
    -0.66
     unborn
    -0.65
     deaf
    -0.64
    */(
    -0.64
     dwar
    -0.63
     wiser
    -0.61
    POSITIVE LOGITS
    iland
    1.02
    opol
    0.96
    oslav
    0.92
    anski
    0.86
    rano
    0.83
    arian
    0.82
    oni
    0.82
    ieri
    0.81
     Ley
    0.81
    ova
    0.78
    Activations Density 0.094%

    No Known Activations