© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 17464
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mistake."

    oai_token-act-pair · gpt-3.5-turbo

    references to mistakes and errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azine
    -0.78
    NetMessage
    -0.67
     GOODMAN
    -0.66
    electric
    -0.64
    Jr
    -0.64
    Jane
    -0.63
    weeney
    -0.63
    packages
    -0.63
    borg
    -0.63
     sights
    -0.62
    POSITIVE LOGITS
     mistakes
    0.94
    fulness
    0.86
     mistake
    0.82
     careless
    0.80
     perpetrated
    0.78
     prone
    0.77
     dece
    0.74
     incurred
    0.74
     corrected
    0.73
     forgiven
    0.72
    Activations Density 0.074%

    No Known Activations