© 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. 6092
    Prev
    Next
    INDEX
    Explanations

    significant actions that can be done with specific information or items

    oai_token-act-pair · gpt-3.5-turbo

    references to data utilization and applications

    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
     truce
    -0.58
     NCT
    -0.58
     Plenty
    -0.57
     Yesterday
    -0.56
    been
    -0.55
     Consent
    -0.55
     Doomsday
    -0.53
     Kirin
    -0.53
     Moder
    -0.52
     ][
    -0.52
    POSITIVE LOGITS
     later
    1.02
     elsewhere
    0.95
     afterwards
    0.89
     afterward
    0.87
     thereafter
    0.84
     wherever
    0.83
     digitally
    0.83
    intern
    0.83
     externally
    0.82
     onto
    0.81
    Activations Density 0.317%

    No Known Activations