© 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. 9-RES-JB
    11. 7270
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotions or levels of intensities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize degrees of intensity or significance

    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
    ropolis
    -0.77
     Related
    -0.75
    itures
    -0.71
    arthed
    -0.71
    estate
    -0.69
    aea
    -0.69
    ezvous
    -0.69
    chnology
    -0.68
    anwhile
    -0.67
    -+-+
    -0.67
    POSITIVE LOGITS
     impunity
    1.28
     ease
    1.21
     precision
    1.15
     abandon
    1.10
     vig
    1.07
     dignity
    1.06
     confidence
    1.05
     caution
    1.04
     gust
    1.04
     haste
    1.01
    Activations Density 0.281%

    No Known Activations