© 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 49152
    9. 8-RES_FS49152-JB
    11. 37532
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts related to environmental and geological sciences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    314
    +0.19
    0.9%
    687
    +0.10
    0.5%
    47
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.19
    0.01
    631
    +0.10
    0.03
    487
    +0.09
    0.03
    Negative Logits
     lockout
    -0.83
     slee
    -0.73
    Interstitial
    -0.68
     strip
    -0.66
     apr
    -0.65
     complying
    -0.64
     refrain
    -0.63
     chained
    -0.63
     Laugh
    -0.63
    ||||
    -0.63
    POSITIVE LOGITS
    biology
    1.33
    odynamics
    1.25
    omics
    1.22
    ology
    1.21
    ological
    1.21
    ologists
    1.20
     sciences
    1.19
    science
    1.18
    Science
    1.16
    ysics
    1.16
    Activations Density 0.080%

    No Known Activations