© 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 EvalsExportsinterp-engineNEWAPI 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. 14560
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements or recognition

    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
    +0.15
    0.7%
    362
    +0.14
    0.6%
    608
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.05
    608
    +0.14
    0.05
    562
    +0.12
    0.04
    Negative Logits
    igate
    -0.76
     Rasm
    -0.75
    soever
    -0.73
    ÑĮ
    -0.73
    CHAPTER
    -0.72
    VI
    -0.71
    isode
    -0.70
    river
    -0.70
    ievers
    -0.69
    trl
    -0.69
    POSITIVE LOGITS
     own
    1.41
     propensity
    1.31
     penchant
    1.30
     inability
    1.23
     tendency
    1.21
     willingness
    1.19
     ability
    1.17
     proximity
    1.14
     lack
    1.13
     insistence
    1.13
    Activations Density 0.160%

    No Known Activations