© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 3072
    9. 8-RES_FS3072-JB
    11. 3054
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, politics, and public figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    7
    +0.15
    0.7%
    496
    +0.11
    0.5%
    432
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.15
    0.07
    232
    +0.11
    0.06
    683
    +0.11
    0.05
    Negative Logits
     hitch
    -0.72
     Canaveral
    -0.66
    enhagen
    -0.59
     shake
    -0.57
    mson
    -0.56
    inal
    -0.56
     MPG
    -0.56
    TPPStreamerBot
    -0.56
     unrecogn
    -0.54
    WD
    -0.54
    POSITIVE LOGITS
    emies
    1.28
    esis
    1.21
    heimer
    1.15
    bach
    1.14
    wald
    1.13
    ocide
    1.10
    berger
    1.09
    zyme
    1.09
    vironment
    1.08
    ews
    1.07
    Activations Density 0.786%

    No Known Activations