© 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. 11643
    Prev
    Next
    INDEX
    Explanations

    phrases related to identifying a specific person or linking an account with a repository

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or people within the text

    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
     guiActiveUnfocused
    -0.79
    union
    -0.68
    formance
    -0.65
    ience
    -0.64
    rast
    -0.63
     readiness
    -0.61
    Activity
    -0.60
    %%%%
    -0.60
    fw
    -0.60
    strip
    -0.60
    POSITIVE LOGITS
     coined
    1.25
     oversaw
    1.25
     invented
    1.11
     pioneered
    1.06
     drafted
    1.05
     initiated
    1.04
     presided
    1.01
     authored
    1.00
     oversees
    1.00
     spearheaded
    0.99
    Activations Density 0.172%

    No Known Activations