© 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. 17996
    Prev
    Next
    INDEX
    Explanations

    terms related to digital platforms and technologies, such as software platforms and technological advancements

    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
    362
    +0.12
    0.6%
    51
    +0.10
    0.5%
    79
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.06
    669
    +0.10
    0.04
    79
    +0.10
    0.04
    Negative Logits
     largeDownload
    -0.90
    ĸļ
    -0.82
    çĶ°
    -0.79
    éĥ
    -0.73
    erity
    -0.71
    wcsstore
    -0.70
     Âł Âł Âł Âł
    -0.69
    moil
    -0.69
    é¾įåĸļ士
    -0.68
    Ô
    -0.67
    POSITIVE LOGITS
     existing
    0.81
     whichever
    0.76
     those
    0.74
     taxp
    0.74
     certain
    0.73
     harmful
    0.70
     frontline
    0.66
     TN
    0.65
     any
    0.65
     locally
    0.64
    Activations Density 0.273%

    No Known Activations