© 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. 15759
    Prev
    Next
    INDEX
    Explanations

    specific quantities or numerical values mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate frequency or regularity in actions or characteristics

    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
     Flavoring
    -0.63
    OTOS
    -0.61
    itol
    -0.57
     Pieces
    -0.56
    Delivery
    -0.55
    Bey
    -0.55
    akin
    -0.54
    GoldMagikarp
    -0.54
    Asset
    -0.53
     Seah
    -0.53
    POSITIVE LOGITS
     aren
    1.10
     deserve
    1.08
     reside
    1.07
     comprise
    1.06
     owe
    1.05
     seem
    1.04
     weren
    1.01
     belong
    1.00
     populate
    1.00
     rely
    1.00
    Activations Density 0.167%

    No Known Activations