© 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. 24422
    Prev
    Next
    INDEX
    Explanations

    adjectives that describe the intensity or magnitude of actions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words indicating significant assessments or evaluations

    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
    lio
    -0.81
    deen
    -0.75
    lass
    -0.75
    raf
    -0.75
    atech
    -0.71
    here
    -0.70
    pherd
    -0.69
    estate
    -0.67
    hedon
    -0.66
    gars
    -0.66
    POSITIVE LOGITS
     exceptions
    1.42
     caveats
    1.34
     exception
    1.27
     impunity
    1.24
     hindsight
    1.22
     ease
    1.08
     caveat
    1.07
     emphasis
    1.06
     flair
    1.06
     vig
    1.04
    Activations Density 0.237%

    No Known Activations