© 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. 14251
    Prev
    Next
    INDEX
    Explanations

    phrases where a question is posed followed by a direct answer, often related to opinions or preferences

    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
    373
    +0.14
    0.6%
    344
    +0.11
    0.5%
    469
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.14
    0.02
    8
    +0.11
    0.02
    348
    +0.10
    0.02
    Negative Logits
    ¥µ
    -0.65
    idi
    -0.63
    ivities
    -0.62
     dealings
    -0.61
     Orient
    -0.60
     activities
    -0.59
     culminated
    -0.57
    iage
    -0.56
     advance
    -0.56
     laun
    -0.56
    POSITIVE LOGITS
     YES
    1.18
     yes
    1.16
    YES
    1.13
    yes
    1.04
     Nope
    0.92
     Yes
    0.83
     affirmative
    0.83
     nil
    0.81
     NO
    0.77
     unequiv
    0.75
    Activations Density 0.110%

    No Known Activations