© 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. 11-RES-JB
    11. 19331
    Prev
    Next
    INDEX
    Explanations

    dates and details about when an article was written or updated

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the publication history of articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¯¯
    -0.76
    uchi
    -0.74
    TY
    -0.66
    mare
    -0.66
     Anger
    -0.66
    ulum
    -0.64
    ometers
    -0.63
     looms
    -0.63
     grounding
    -0.62
    thur
    -0.60
    POSITIVE LOGITS
     edited
    1.25
     amended
    1.16
     reprinted
    1.16
     updated
    1.14
     published
    1.10
     written
    1.10
     authored
    1.06
     condensed
    1.06
     translated
    1.05
     originally
    1.04
    Activations Density 0.063%

    No Known Activations