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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20828
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to noticing or being aware of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of perception and awareness-related actions

    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
    ioxide
    -0.74
    ActionCode
    -0.70
    terness
    -0.69
     subur
    -0.68
    Ý
    -0.68
     pione
    -0.67
    é¾įå¥
    -0.67
    £ı
    -0.67
    Ą
    -0.67
    -0.67
    POSITIVE LOGITS
     us
    0.99
     yours
    0.95
     me
    0.89
     your
    0.88
     you
    0.83
     theirs
    0.82
     ours
    0.82
     hers
    0.82
    SPONSORED
    0.73
     my
    0.72
    Activations Density 0.377%

    No Known Activations