© 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 24576
    9. 8-RES_FS24576-JB
    11. 18908
    Prev
    Next
    INDEX
    Explanations

    discussions related to official agreements with concerns about disclosure and potential controversy

    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
    571
    +0.12
    0.5%
    481
    +0.12
    0.5%
    462
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    571
    +0.12
    0.04
    298
    +0.12
    0.03
    462
    +0.10
    0.03
    Negative Logits
    aturdays
    -0.76
     commend
    -0.74
    ichick
    -0.70
    thank
    -0.69
     admirable
    -0.67
    hest
    -0.65
    oln
    -0.65
    cellence
    -0.64
    heres
    -0.63
    ISTORY
    -0.62
    POSITIVE LOGITS
     jeopard
    0.99
     repr
    0.96
     contam
    0.96
     inadvertently
    0.94
     misinterpret
    0.93
     repercussions
    0.93
     miscon
    0.92
     encro
    0.90
     retribution
    0.89
     someday
    0.89
    Activations Density 0.424%

    No Known Activations