© 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. 2002
    Prev
    Next
    INDEX
    Explanations

    references to economic activities or transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific actions or events that have clear implications or consequences

    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
     assorted
    -0.52
     redes
    -0.52
    rather
    -0.48
    ãĥĩãĤ£
    -0.48
    ortment
    -0.47
     strengthened
    -0.47
    okingly
    -0.45
     periodically
    -0.45
    oso
    -0.45
    éĩ
    -0.44
    POSITIVE LOGITS
     nor
    1.95
     anymore
    1.80
    nor
    1.32
     whatsoever
    1.21
     anything
    1.14
     slightest
    1.12
     any
    1.07
     anywhere
    1.05
     anybody
    1.04
    yet
    0.99
    Activations Density 1.383%

    No Known Activations