© 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 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. 17563
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming terms, especially related to async methods and variable manipulations

    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
    +0.56
    4.3%
    87
    +0.52
    3.9%
    481
    +0.14
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.56
    -0.00
    373
    +0.52
    -0.10
    756
    +0.14
    -0.05
    Negative Logits
     Belfast
    -0.40
    reys
    -0.35
    osponsors
    -0.34
     Originally
    -0.34
     âĢº
    -0.33
    æ©Ł
    -0.33
    ickr
    -0.32
    iq
    -0.32
    accompanied
    -0.32
    ibaba
    -0.31
    POSITIVE LOGITS
    ]."
    0.61
    )."
    0.58
    .'"
    0.55
    '."
    0.55
    .")
    0.51
    .''.
    0.49
    .''
    0.48
    .</
    0.48
    ."
    0.48
    .).
    0.47
    Activations Density 3.361%

    No Known Activations