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

    Neuronpedia

    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. 11842
    Prev
    Next
    INDEX
    Explanations

    specific references to a particular situation or scenario

    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
    599
    +0.10
    0.5%
    550
    +0.10
    0.5%
    348
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    348
    +0.10
    0.02
    460
    +0.10
    0.02
    599
    +0.09
    0.02
    Negative Logits
    itely
    -0.74
    olor
    -0.73
    kefeller
    -0.70
    icc
    -0.69
    rush
    -0.67
    osponsors
    -0.67
    harm
    -0.65
    asionally
    -0.64
    jriwal
    -0.64
    ogether
    -0.63
    POSITIVE LOGITS
    mma
    0.65
    ndra
    0.65
    gency
    0.61
    abouts
    0.60
    ãĥķãĤ©
    0.58
    >>>>>>>>
    0.57
    photo
    0.57
     Hyundai
    0.57
     anyway
    0.57
    notes
    0.56
    Activations Density 0.027%

    No Known Activations