© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 20473
    Prev
    Next
    INDEX
    Explanations

    programming related keywords and error messages

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and error messages related to software programming or syntax issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gobl
    -1.07
     dwar
    -0.99
     skelet
    -0.92
     cous
    -0.91
     coh
    -0.91
     elves
    -0.90
     dwarves
    -0.90
     kale
    -0.89
     goblins
    -0.88
     dragons
    -0.87
    POSITIVE LOGITS
     Label
    1.55
     Publication
    1.41
     Condition
    1.37
     Finish
    1.37
     Submission
    1.36
     Character
    1.36
     Output
    1.35
     Trial
    1.35
     Drop
    1.35
     Message
    1.35
    Activations Density 0.301%

    No Known Activations