Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 43325
    Prev
    Next
    INDEX
    Explanations

    references to ants

    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
    623
    +0.14
    0.6%
    228
    +0.11
    0.5%
    59
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    623
    +0.14
    0.01
    59
    +0.11
    0.01
    19
    +0.11
    0.01
    Negative Logits
     Cay
    -0.73
     Tycoon
    -0.70
     Stras
    -0.66
    UTION
    -0.65
     Exile
    -0.65
     Jenner
    -0.64
    displayText
    -0.64
     Drawn
    -0.63
     Goo
    -0.63
     Skydragon
    -0.63
    POSITIVE LOGITS
    idepress
    1.25
    icip
    1.21
    agonists
    1.18
    ioch
    1.15
    agonist
    1.10
    irez
    1.05
    imus
    1.05
    rax
    1.02
    onyms
    1.02
    ipop
    1.01
    Activations Density 0.007%

    No Known Activations