© 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. 0-RES-JB
    11. 17945
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the need for correcting errors or mistakes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "correct" and its variations, indicating a focus on the theme of correction and adjustments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ihad
    -0.66
    mens
    -0.62
    terror
    -0.60
    ottenham
    -0.59
     ties
    -0.59
    ancy
    -0.59
    abal
    -0.59
     Ride
    -0.59
    ppings
    -0.58
    whelming
    -0.58
    POSITIVE LOGITS
     corrected
    3.78
     correcting
    2.38
     correction
    2.38
    correct
    2.04
     corrective
    1.71
     corrections
    1.68
     Correct
    1.65
     correct
    1.60
     repaired
    1.53
    Correct
    1.53
    Activations Density 0.017%

    No Known Activations