© 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. 5169
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and behavioral responses

    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
    102
    +0.14
    0.6%
    55
    +0.11
    0.5%
    418
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.14
    0.04
    55
    +0.11
    0.04
    418
    +0.11
    0.03
    Negative Logits
    oleon
    -0.67
    sonian
    -0.66
     Ples
    -0.66
    Reply
    -0.65
     Kamp
    -0.65
     Recession
    -0.62
     Myth
    -0.60
     Puzzle
    -0.60
     scrimmage
    -0.59
     Blocks
    -0.59
    POSITIVE LOGITS
    hemoth
    1.41
    heading
    1.30
    arers
    1.28
    ardless
    1.18
    fitting
    1.16
    acons
    1.16
    getting
    1.11
    ijing
    1.10
    ige
    1.10
    yond
    1.10
    Activations Density 0.058%

    No Known Activations