© 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. 4408
    Prev
    Next
    INDEX
    Explanations

    descriptions related to product features and recommendations

    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
    480
    +0.44
    2.2%
    244
    +0.12
    0.6%
    266
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.44
    0.01
    266
    +0.12
    0.07
    244
    +0.11
    0.05
    Negative Logits
    çīĪ
    -0.80
    ©¶æ¥µ
    -0.78
     Moroc
    -0.65
    senal
    -0.64
    ãĤ´ãĥ³
    -0.64
    enegger
    -0.61
    landish
    -0.59
    eteenth
    -0.58
     enthusi
    -0.58
    ãĥķ
    -0.56
    POSITIVE LOGITS
     slightest
    0.74
     sufficiently
    0.72
     somebody
    0.71
     fails
    0.71
     please
    0.68
    pires
    0.64
     >=
    0.64
     something
    0.63
     <=
    0.62
     disagree
    0.60
    Activations Density 0.637%

    No Known Activations