© 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. 9-RES-JB
    11. 11210
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to correcting something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "correct."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atos
    -0.97
     Pry
    -0.72
    CHO
    -0.72
    nam
    -0.72
    thin
    -0.71
    atten
    -0.71
     Valhalla
    -0.71
    bang
    -0.70
    NetMessage
    -0.69
    aden
    -0.66
    POSITIVE LOGITS
     spelling
    1.00
     misinformation
    0.94
     inaccur
    0.84
     erroneous
    0.83
    able
    0.81
     pronunciation
    0.79
    ibly
    0.76
    fully
    0.74
    ions
    0.74
    orate
    0.74
    Activations Density 0.042%

    No Known Activations