© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18287
    Prev
    Next
    INDEX
    Explanations

    references to changes or transitions between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with music and entertainment

    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
    ONSORED
    -0.52
    onto
    -0.51
     helicop
    -0.50
    Instead
    -0.48
    STEP
    -0.48
     withdraw
    -0.47
     THEN
    -0.47
     withdrew
    -0.47
    arettes
    -0.46
    arations
    -0.46
    POSITIVE LOGITS
     fascination
    0.70
    pmwiki
    0.70
     fascinated
    0.66
     often
    0.65
     rumours
    0.63
    catentry
    0.63
     understandably
    0.63
     misconception
    0.62
     lately
    0.62
     misconceptions
    0.62
    Activations Density 1.055%

    No Known Activations