© 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. 5464
    Prev
    Next
    INDEX
    Explanations

    information or details about various items or topics

    oai_token-act-pair · gpt-3.5-turbo

    general categories of information and items

    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
    vati
    -0.68
     hindsight
    -0.64
    TW
    -0.63
    escription
    -0.63
    ixties
    -0.63
    IPS
    -0.62
    terday
    -0.60
    iversary
    -0.60
    nin
    -0.60
    xon
    -0.60
    POSITIVE LOGITS
     thereof
    1.07
     pertaining
    1.06
     related
    1.03
     relating
    1.02
     pertinent
    0.97
     relevant
    0.96
     imaginable
    0.95
     alike
    0.94
     besides
    0.91
     associated
    0.91
    Activations Density 0.235%

    No Known Activations