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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15250
    Prev
    Next
    INDEX
    Explanations

    dates and software-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to version updates and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arious
    -0.80
     predomin
    -0.68
     oneself
    -0.67
     commer
    -0.66
     ponder
    -0.65
    opian
    -0.64
    ogie
    -0.64
    essional
    -0.62
     cove
    -0.61
     whence
    -0.60
    POSITIVE LOGITS
    Fixed
    1.88
    Added
    1.74
     Fixed
    1.72
     Added
    1.63
    Removed
    1.62
     Fixes
    1.60
    Changed
    1.58
     Removed
    1.56
     Changed
    1.54
    Improved
    1.52
    Activations Density 0.148%

    No Known Activations