© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7329
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial or sensitive topics

    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
    +0.12
    0.6%
    304
    +0.10
    0.5%
    515
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    501
    +0.12
    0.02
    715
    +0.10
    0.02
    515
    +0.10
    0.02
    Negative Logits
    è¦ļéĨĴ
    -0.90
    VERTISEMENT
    -0.81
    MpServer
    -0.79
    SourceFile
    -0.78
    æ©
    -0.70
    ãĤ´
    -0.65
    conom
    -0.62
    Interstitial
    -0.61
     teasp
    -0.59
     pione
    -0.59
    POSITIVE LOGITS
    adays
    1.04
    herer
    0.94
     suppose
    0.86
     imagine
    0.85
    here
    0.83
     begs
    0.82
     admittedly
    0.77
     THERE
    0.74
     let
    0.72
     secondly
    0.71
    Activations Density 0.055%

    No Known Activations