© 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. 13571
    Prev
    Next
    INDEX
    Explanations

    mentions of the words "you" and "Whenever"

    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
    447
    +0.66
    6.0%
    87
    +0.49
    4.5%
    64
    +0.08
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.66
    -0.01
    464
    +0.49
    0.06
    326
    +0.08
    0.16
    Negative Logits
    eaturing
    -0.31
     latter
    -0.30
    ONSORED
    -0.29
     thereof
    -0.28
    heid
    -0.27
    ROR
    -0.27
     guiActiveUnfocused
    -0.26
     thereto
    -0.26
    AppData
    -0.25
     homegrown
    -0.24
    POSITIVE LOGITS
    pload
    0.33
    endum
    0.32
     Gard
    0.31
    zsche
    0.29
    ¶
    0.28
    ©¶æ
    0.28
     Canaver
    0.26
     Balls
    0.26
    è¦ļéĨĴ
    0.26
     Anthropology
    0.25
    Activations Density 4.247%

    No Known Activations