© 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 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. 43067
    Prev
    Next
    INDEX
    Explanations

    references to Tunisia and Trinidad

    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
    288
    +0.14
    0.6%
    612
    +0.13
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.14
    0.01
    288
    +0.13
    0.01
    55
    +0.12
    0.01
    Negative Logits
    bilt
    -0.95
    lasses
    -0.83
    effic
    -0.83
    croft
    -0.78
    alach
    -0.75
    loss
    -0.75
    ucl
    -0.69
    ving
    -0.66
    rint
    -0.66
    icago
    -0.65
    POSITIVE LOGITS
     Airways
    0.94
     Tunisia
    0.84
     Tunis
    0.83
    ophobia
    0.79
     Tanz
    0.78
    ian
    0.78
    etta
    0.76
    ophobic
    0.76
    ienne
    0.74
    essa
    0.72
    Activations Density 0.002%

    No Known Activations