Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 19625
    Prev
    Next
    INDEX
    Explanations

    instances where someone is aware of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "aware" indicating consciousness or knowledge of a situation

    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
    quer
    -0.63
    NOR
    -0.53
    ramid
    -0.53
    ueller
    -0.53
    enegger
    -0.53
    irrel
    -0.52
    ordinary
    -0.52
    olicy
    -0.51
    Textures
    -0.51
    eu
    -0.50
    POSITIVE LOGITS
     of
    1.30
     thereof
    1.18
     OF
    1.05
    Of
    1.03
    of
    0.95
     Of
    0.94
    ledged
    0.86
    ledge
    0.84
     that
    0.78
    OF
    0.78
    Activations Density 0.079%

    No Known Activations