© 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 24576
    9. 8-RES_FS24576-JB
    11. 9806
    Prev
    Next
    INDEX
    Explanations

    words related to raising one's voice or expressing strong opinions

    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
    97
    +0.11
    0.5%
    535
    +0.10
    0.5%
    734
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.11
    0.02
    288
    +0.10
    0.02
    503
    +0.10
    0.01
    Negative Logits
     Panther
    -0.68
     rule
    -0.65
     Sachs
    -0.64
     Kimber
    -0.63
     Daddy
    -0.63
     Sahara
    -0.63
     striking
    -0.62
     secrecy
    -0.61
     Robin
    -0.61
     Dynasty
    -0.61
    POSITIVE LOGITS
    abulary
    1.38
    ally
    1.29
    ational
    1.18
    ations
    1.16
    ates
    1.14
    iferation
    1.12
    ationally
    1.07
    ifer
    1.05
    alf
    1.02
    acy
    1.02
    Activations Density 0.039%

    No Known Activations