© 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. 10277
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and government actions

    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
    36
    +0.26
    1.3%
    343
    +0.13
    0.6%
    314
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.26
    0.07
    343
    +0.13
    0.04
    263
    +0.13
    0.03
    Negative Logits
     Ampl
    -0.72
     ATK
    -0.71
    alion
    -0.67
     OPS
    -0.67
     amplification
    -0.66
     Atkins
    -0.65
     AoE
    -0.63
     indign
    -0.62
     Allied
    -0.61
     Izan
    -0.61
    POSITIVE LOGITS
    ria
    1.18
    lder
    1.15
    eon
    1.13
    uras
    1.10
    sembly
    1.06
    ces
    1.05
    pron
    1.04
    ld
    1.04
    merce
    1.03
    ñ
    1.03
    Activations Density 0.132%

    No Known Activations