© 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. 8-RES-JB
    11. 20267
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions related to software updates and bug fixes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to updates and changes in software or digital content

    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
    bowl
    -0.77
    sonian
    -0.74
    igree
    -0.69
     Cathy
    -0.66
     Martha
    -0.66
    llah
    -0.65
     Byrd
    -0.65
     legally
    -0.62
    uminati
    -0.62
     Feinstein
    -0.61
    POSITIVE LOGITS
    Fixed
    1.33
    Added
    1.33
     Fixes
    1.31
    Improve
    1.28
    Improved
    1.24
    FIX
    1.19
     Improvements
    1.18
    Removed
    1.18
     Fixed
    1.18
    Fix
    1.18
    Activations Density 0.215%

    No Known Activations