© 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. 8-RES-JB
    11. 3181
    Prev
    Next
    INDEX
    Explanations

    Java programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and class identifiers in the context of programming or sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
     Beef
    -0.98
    Pg
    -0.95
     Trails
    -0.94
    Args
    -0.93
     Dip
    -0.91
     Sauce
    -0.89
     Chero
    -0.87
    Lua
    -0.86
     Practices
    -0.85
     Strategies
    -0.84
    POSITIVE LOGITS
     exhib
    0.86
     hover
    0.85
     agg
    0.84
     mand
    0.82
     princ
    0.80
     vit
    0.80
     grid
    0.79
     mult
    0.78
     misc
    0.78
     collide
    0.78
    Activations Density 0.589%

    No Known Activations