© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 20434
    Prev
    Next
    INDEX
    Explanations

    mentions of presenting or showing things to a wide audience like "the world."

    oai_token-act-pair · gpt-3.5-turbo

    topics related to sharing experiences and engaging with a community

    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
     Theft
    -0.61
    orts
    -0.59
     prev
    -0.56
     Misc
    -0.55
     compared
    -0.55
    lander
    -0.54
     Brawl
    -0.54
     Renaissance
    -0.53
    ivism
    -0.53
     Personally
    -0.53
    POSITIVE LOGITS
     via
    0.99
     subscribers
    0.82
     coffers
    0.78
    omever
    0.77
    umers
    0.77
     doorstep
    0.76
     orally
    0.75
     creditors
    0.74
     audiences
    0.74
    holders
    0.73
    Activations Density 0.409%

    No Known Activations