© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 3410
    Prev
    Next
    INDEX
    Explanations

    keywords related to image attribution and possibly sources or credits

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to stock images and photography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettes
    -0.65
    wu
    -0.62
     incent
    -0.60
    RIC
    -0.58
    knit
    -0.58
     PLA
    -0.57
     intervening
    -0.57
    IENT
    -0.57
     Doctrine
    -0.56
    ew
    -0.56
    POSITIVE LOGITS
     Shutterstock
    0.85
    Magazine
    0.79
     IMAGES
    0.78
    xual
    0.75
     Thumbnails
    0.74
    imgur
    0.70
    sung
    0.70
    idth
    0.70
    ãĤ¼ãĤ¦ãĤ¹
    0.70
    ãĥķãĤ©
    0.68
    Activations Density 0.058%

    No Known Activations