© 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. 41161
    Prev
    Next
    INDEX
    Explanations

    terms related to semiconductors and their components

    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
    288
    +0.16
    0.7%
    620
    +0.13
    0.6%
    668
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.02
    578
    +0.13
    0.01
    647
    +0.11
    0.01
    Negative Logits
    spell
    -0.81
     sober
    -0.76
    mire
    -0.72
     Shelter
    -0.72
    lez
    -0.70
     unaccompanied
    -0.66
     Homeless
    -0.65
    uca
    -0.64
    FK
    -0.64
     Guerrero
    -0.64
    POSITIVE LOGITS
    onductor
    1.31
     architectures
    1.06
     manufacturing
    1.04
     filament
    0.98
     manufactures
    0.98
     semic
    0.96
     technologies
    0.96
     technology
    0.95
     silicon
    0.93
     fabrication
    0.91
    Activations Density 0.025%

    No Known Activations