© 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. 17319
    Prev
    Next
    INDEX
    Explanations

    mentions of covering something physically, whether it be faces, expenses, or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to covering faces or protecting identities

    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
    Enh
    -0.68
    ________________________________________________________________
    -0.63
    nos
    -0.61
     Pastebin
    -0.61
    bour
    -0.61
    sonian
    -0.60
     compr
    -0.59
     luck
    -0.58
     hating
    -0.57
    nir
    -0.57
    POSITIVE LOGITS
     bases
    1.22
     tracks
    0.94
     entirety
    0.92
    phia
    0.89
     shortfall
    0.87
     costs
    0.85
     gaps
    0.83
     distances
    0.78
    idential
    0.77
     upfront
    0.76
    Activations Density 0.116%

    No Known Activations