© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8328
    Prev
    Next
    INDEX
    Explanations

    specific instances of the term "Classic"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Classic" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ashore
    -0.72
     corpor
    -0.70
    aff
    -0.70
     officer
    -0.69
    intent
    -0.69
    agging
    -0.69
     strength
    -0.68
    govern
    -0.67
     imprisoned
    -0.66
     shack
    -0.66
    POSITIVE LOGITS
     Classic
    3.83
    Classic
    2.65
    classic
    2.08
     Classics
    1.99
     classic
    1.52
     Vintage
    1.43
     classics
    1.34
     Classical
    1.30
     Retro
    1.11
     Mini
    1.10
    Activations Density 0.016%

    No Known Activations