© 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. 20928
    Prev
    Next
    INDEX
    Explanations

    grammatical errors within texts

    oai_token-act-pair · gpt-3.5-turbo

    references to grammatical issues and editing processes

    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
    competitive
    -0.78
    pires
    -0.74
    wake
    -0.72
    inea
    -0.72
    seekers
    -0.72
    iership
    -0.72
    ibaba
    -0.71
    consumer
    -0.70
    ggle
    -0.70
    oppable
    -0.70
    POSITIVE LOGITS
     edits
    1.69
     corrections
    1.55
     formatting
    1.51
     typo
    1.44
     edited
    1.39
     delet
    1.37
     annotations
    1.37
     corrected
    1.34
     editing
    1.30
     deleted
    1.28
    Activations Density 0.615%

    No Known Activations