© 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. 20759
    Prev
    Next
    INDEX
    Explanations

    words related to the company or service named "Sky"

    oai_token-act-pair · gpt-3.5-turbo

    references to the media company "Sky."

    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
    ional
    -0.71
     sanity
    -0.70
     menstru
    -0.65
     Schne
    -0.65
    女
    -0.64
    Ñĭ
    -0.63
     thous
    -0.63
    âĶĢ
    -0.62
    ually
    -0.62
     snail
    -0.60
    POSITIVE LOGITS
    landers
    1.00
    rocket
    0.98
    Train
    0.97
    hawks
    0.95
    lake
    0.91
    lar
    0.91
    rock
    0.89
    ping
    0.88
    hawk
    0.87
    pes
    0.86
    Activations Density 0.026%

    No Known Activations