© 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. 6616
    Prev
    Next
    INDEX
    Explanations

    financial terms and market-related information

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to various fields or subjects

    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
     thereto
    -0.61
     encomp
    -0.59
     thereof
    -0.59
     unaccompanied
    -0.58
     âĢ¦"
    -0.57
     pokemon
    -0.56
     ..."
    -0.56
     respectively
    -0.55
     whenever
    -0.54
     trans
    -0.53
    POSITIVE LOGITS
    ibliography
    0.93
    ogether
    0.81
     Profile
    0.79
     References
    0.75
     Thoughts
    0.75
     Differences
    0.75
    abases
    0.72
    ustration
    0.72
    cerpt
    0.72
     Comparison
    0.71
    Activations Density 0.531%

    No Known Activations