© 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. 21249
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to policy revisions or updates in official statements

    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
    iquid
    -0.77
     looted
    -0.75
    ebted
    -0.75
    photos
    -0.71
     manif
    -0.70
     evict
    -0.70
    ghost
    -0.68
    aunder
    -0.67
    abilia
    -0.67
    gencies
    -0.66
    POSITIVE LOGITS
     guideline
    1.23
     guidelines
    1.23
     consensus
    1.20
     Recommend
    1.18
     Guidelines
    1.15
     recommendations
    1.10
     Pediatrics
    1.09
     AMA
    1.08
     FDA
    1.08
     Standards
    1.07
    Activations Density 0.725%

    No Known Activations