© 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. 24047
    Prev
    Next
    INDEX
    Explanations

    mentions of countries and their related institutions or events

    oai_token-act-pair · gpt-3.5-turbo

    plural forms of nouns

    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
     Lauder
    -0.57
    epad
    -0.55
     assumes
    -0.54
     accompanied
    -0.53
     Misc
    -0.52
     Hubbard
    -0.51
    Spoiler
    -0.51
     disclaim
    -0.51
     something
    -0.51
    Keefe
    -0.51
    POSITIVE LOGITS
    largest
    1.07
     largest
    1.06
     tallest
    0.95
     longest
    0.89
     oldest
    0.89
     finest
    0.88
    apest
    0.87
     poorest
    0.86
     premier
    0.86
     foremost
    0.84
    Activations Density 0.110%

    No Known Activations