© 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. 7-RES-JB
    11. 12477
    Prev
    Next
    INDEX
    Explanations

    mentions of people knowing or being aware of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of knowledge or awareness about situations or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    livion
    -0.67
    ramid
    -0.66
     Featured
    -0.65
     topp
    -0.64
    enture
    -0.64
    uctions
    -0.63
     detrim
    -0.62
     contention
    -0.61
     dissolution
    -0.61
    Rog
    -0.61
    POSITIVE LOGITS
     KNOW
    0.74
     Knowing
    0.72
     Detect
    0.72
    knowledge
    0.68
    Knowing
    0.67
    vez
    0.67
    Know
    0.66
     Plain
    0.66
     Knowledge
    0.66
     intuitive
    0.65
    Activations Density 0.586%

    No Known Activations