© 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. 22788
    Prev
    Next
    INDEX
    Explanations

    introductory phrases and structures that lead into discussions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.13
    0.6%
    748
    +0.10
    0.4%
    503
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    250
    +0.13
    0.03
    155
    +0.10
    0.04
    435
    +0.09
    0.02
    Negative Logits
    lees
    -0.83
    utm
    -0.71
    tumblr
    -0.70
    ald
    -0.69
    nell
    -0.65
    usc
    -0.62
    ³
    -0.60
    soever
    -0.59
    aden
    -0.59
    hung
    -0.59
    POSITIVE LOGITS
     basics
    1.02
     briefly
    0.93
     nutshell
    0.89
     ourselves
    0.86
     analogy
    0.84
     terminology
    0.80
    Background
    0.78
     primer
    0.78
     definitions
    0.77
     recap
    0.77
    Activations Density 0.239%

    No Known Activations