© 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. 11-RES-JB
    11. 1543
    Prev
    Next
    INDEX
    Explanations

    phrases indicating apologies or errors

    oai_token-act-pair · gpt-3.5-turbo

    apologies or expressions of regret in communication

    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
    ï¸ı
    -0.73
    llah
    -0.65
    orge
    -0.63
    fman
    -0.61
    mart
    -0.61
    rouse
    -0.58
    ament
    -0.57
    rette
    -0.57
     fitt
    -0.56
    fter
    -0.56
    POSITIVE LOGITS
    avascript
    0.85
    Invalid
    0.76
     Failed
    0.71
    Sorry
    0.66
    inventoryQuantity
    0.66
     expired
    0.61
    osaurs
    0.60
     Unable
    0.59
     Cannot
    0.59
    ought
    0.59
    Activations Density 0.052%

    No Known Activations