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

    Neuronpedia

    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. 16483
    Prev
    Next
    INDEX
    Explanations

    words related to adding layers or levels to things

    oai_token-act-pair · gpt-3.5-turbo

    references to contributions or additions, particularly in terms of value or importance

    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
    meet
    -0.86
     WATCHED
    -0.85
     outnumbered
    -0.79
    existent
    -0.78
    hung
    -0.78
     Cosponsors
    -0.78
    skip
    -0.73
    existing
    -0.72
    ©¶æ
    -0.72
    payment
    -0.68
    POSITIVE LOGITS
     insight
    1.35
     clarity
    1.24
     nuance
    1.22
     optimism
    1.20
     realism
    1.13
     warmth
    1.11
     insights
    1.09
     credibility
    1.08
     confidence
    1.07
     firepower
    1.05
    Activations Density 0.262%

    No Known Activations