© 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. 9-RES-JB
    11. 15368
    Prev
    Next
    INDEX
    Explanations

    descriptions related to software updates and improvements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software updates and improvements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cathy
    -0.72
    ussia
    -0.71
    tarians
    -0.70
    oldemort
    -0.67
     sor
    -0.67
    bred
    -0.66
     Berm
    -0.65
     Connie
    -0.65
    iott
    -0.65
     eth
    -0.65
    POSITIVE LOGITS
     improvements
    1.32
     enhancements
    1.26
    Changes
    1.23
     Improvements
    1.22
     update
    1.21
     tweaks
    1.19
     additions
    1.19
     fixes
    1.15
     updates
    1.14
     Updates
    1.14
    Activations Density 0.750%

    No Known Activations