© 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. 12032
    Prev
    Next
    INDEX
    Explanations

    scientific or technical terms related to space exploration

    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
    659
    +0.12
    0.5%
    549
    +0.10
    0.5%
    204
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.12
    0.02
    261
    +0.10
    0.01
    669
    +0.10
    0.01
    Negative Logits
    apest
    -0.88
    ãĤ¤ãĥĪ
    -0.72
    umbnails
    -0.69
     Pigs
    -0.68
    jee
    -0.67
     Exhibit
    -0.67
    gey
    -0.66
     Bye
    -0.66
    ICA
    -0.65
    itto
    -0.65
    POSITIVE LOGITS
     depths
    0.97
     pockets
    0.95
     trenches
    0.92
     darkest
    0.90
     dug
    0.83
     deep
    0.83
     penetrating
    0.83
     recess
    0.82
     abyss
    0.82
     trench
    0.81
    Activations Density 0.065%

    No Known Activations