© 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. 12358
    Prev
    Next
    INDEX
    Explanations

    words related to sharing experiences or offering advice

    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
    687
    +0.12
    0.5%
    591
    +0.09
    0.4%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.06
    665
    +0.09
    0.06
    750
    +0.09
    0.04
    Negative Logits
    catentry
    -0.72
    utenberg
    -0.70
     paced
    -0.60
     guiIcon
    -0.58
    obile
    -0.58
    cffffcc
    -0.57
    uble
    -0.57
    è¦ļéĨĴ
    -0.57
    interstitial
    -0.56
     recru
    -0.56
    POSITIVE LOGITS
     themselves
    1.21
     theirs
    1.04
    enance
    0.94
     THEIR
    0.85
    their
    0.83
     yourselves
    0.82
     their
    0.82
     ;)
    0.72
    ingly
    0.70
     anything
    0.69
    Activations Density 0.525%

    No Known Activations