© 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. 6-RES-JB
    11. 13633
    Prev
    Next
    INDEX
    Explanations

    references to sharing or uploading of images or videos on social media platforms

    oai_token-act-pair · gpt-3.5-turbo

    content related to photos and their attributes on social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Presbyterian
    -0.82
     Immunity
    -0.75
    heit
    -0.72
     Methodist
    -0.72
    volent
    -0.72
    oleon
    -0.69
    ivism
    -0.69
     appoint
    -0.68
     attrition
    -0.67
     presiding
    -0.67
    POSITIVE LOGITS
    phot
    1.07
     depict
    0.97
    photos
    0.97
     uploaded
    0.95
     footage
    0.95
    Phot
    0.93
    DragonMagazine
    0.92
    umbnails
    0.92
     upload
    0.92
     photographs
    0.91
    Activations Density 0.535%

    No Known Activations