© 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 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. 9-RES-JB
    11. 15859
    Prev
    Next
    INDEX
    Explanations

    the expression "All in all."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in all" and variations of it

    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
     Reincarn
    -0.66
     offending
    -0.61
    sworth
    -0.60
     preced
    -0.59
     FTA
    -0.57
    gaard
    -0.56
     abortions
    -0.56
     anomalies
    -0.55
     Errors
    -0.54
    ALSE
    -0.54
    POSITIVE LOGITS
    clusive
    1.20
    clus
    0.84
    clusively
    0.82
    CLUS
    0.80
    effic
    0.79
    offensive
    0.79
     vain
    0.75
    ane
    0.75
    lining
    0.74
    expensive
    0.73
    Activations Density 0.070%

    No Known Activations