© 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. 1975
    Prev
    Next
    INDEX
    Explanations

    calls to action or demands for a change or reform

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating proposed changes or reforms

    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
     Cosponsors
    -0.73
    horn
    -0.62
     foss
    -0.62
    sky
    -0.60
     apart
    -0.58
    usercontent
    -0.58
     bundles
    -0.56
    typ
    -0.56
    breaks
    -0.55
    rep
    -0.55
    POSITIVE LOGITS
     accompany
    1.21
     ensure
    1.19
     appease
    1.14
     occur
    1.13
    ggles
    1.09
     accommodate
    1.08
     overcome
    1.06
     enhance
    1.05
     avoid
    1.04
     minimize
    1.03
    Activations Density 0.272%

    No Known Activations