© 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 24576
    9. 8-RES_FS24576-JB
    11. 10933
    Prev
    Next
    INDEX
    Explanations

    references to cultural and political events related to different regions and countries

    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
    481
    +0.18
    0.8%
    425
    +0.12
    0.6%
    408
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    425
    +0.18
    0.04
    380
    +0.12
    0.03
    599
    +0.12
    0.03
    Negative Logits
    elta
    -0.81
    apult
    -0.73
    obin
    -0.72
    zon
    -0.72
    ]);
    -0.68
    manac
    -0.68
    DEN
    -0.66
    iously
    -0.66
    Reason
    -0.65
    è¦ļéĨĴ
    -0.64
    POSITIVE LOGITS
     meanwhile
    1.25
     where
    0.99
     however
    0.97
    where
    0.88
     moreover
    0.81
     birthplace
    0.76
     there
    0.75
    there
    0.68
     mobs
    0.67
     we
    0.63
    Activations Density 0.147%

    No Known Activations