© 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. 7526
    Prev
    Next
    INDEX
    Explanations

    technical or critical software terms

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating difficulty or frustration

    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
    DragonMagazine
    -0.76
    oday
    -0.76
     Horizons
    -0.72
    empl
    -0.72
    isSpecialOrderable
    -0.71
     Celebr
    -0.71
    aughs
    -0.70
    facts
    -0.70
    odiac
    -0.70
     Recogn
    -0.70
    POSITIVE LOGITS
     cumbersome
    1.61
     unreliable
    1.50
     inefficient
    1.48
     bulky
    1.47
     buggy
    1.42
     expensive
    1.38
     tedious
    1.38
     impractical
    1.37
     noisy
    1.35
     inconvenient
    1.35
    Activations Density 0.328%

    No Known Activations