© 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. 187
    Prev
    Next
    INDEX
    Explanations

    mentions related to technical tasks and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to procedures or instructions

    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
     paralle
    -0.66
     tast
    -0.62
     hosp
    -0.62
     funnel
    -0.61
     scrambling
    -0.61
     sticking
    -0.61
     soaking
    -0.60
     heck
    -0.60
     carving
    -0.59
     funky
    -0.59
    POSITIVE LOGITS
    Synopsis
    1.20
    Contents
    1.15
    rawdownloadcloneembedreportprint
    0.99
    Example
    0.91
    Disclaimer
    0.90
    Trivia
    0.88
    Summary
    0.88
    Reason
    0.87
    Statistics
    0.85
    Written
    0.85
    Activations Density 0.770%

    No Known Activations