© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1418
    Prev
    Next
    INDEX
    Explanations

    numbers and fractions

    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
    241
    +0.10
    0.5%
    162
    +0.10
    0.4%
    744
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    119
    +0.10
    0.04
    8
    +0.10
    0.05
    241
    +0.09
    0.04
    Negative Logits
    ]),
    -0.78
    arthed
    -0.76
    umbn
    -0.74
    è¦ļéĨĴ
    -0.67
    ounter
    -0.67
     Mehran
    -0.65
    bryce
    -0.59
     guiActiveUnfocused
    -0.59
     prospect
    -0.59
    arthy
    -0.59
    POSITIVE LOGITS
    cknow
    0.95
     kidding
    0.88
    Cause
    0.87
    HAHAHAHA
    0.82
     gotta
    0.80
    cknowled
    0.77
     ain
    0.76
     wanna
    0.73
     Stupid
    0.71
    eday
    0.71
    Activations Density 0.403%

    No Known Activations