© 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. 5451
    Prev
    Next
    INDEX
    Explanations

    code snippets related to web development, specifically Django

    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
    0.7%
    553
    +0.09
    0.4%
    501
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.14
    0.02
    701
    +0.09
    0.02
    373
    +0.09
    -0.01
    Negative Logits
    TPPStreamerBot
    -0.78
    )</
    -0.78
    è¦ļéĨĴ
    -0.75
    ),"
    -0.75
    ±
    -0.74
    =-=-=-=-
    -0.72
    é¾įåĸļ士
    -0.70
    bsp
    -0.70
    judicial
    -0.68
    },{"
    -0.68
    POSITIVE LOGITS
     ,
    0.81
     )
    0.76
     .)
    0.73
     ]
    0.71
     ;
    0.69
     :
    0.68
     .
    0.68
     specs
    0.67
     mil
    0.66
     cess
    0.64
    Activations Density 0.028%

    No Known Activations