© 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. 10048
    Prev
    Next
    INDEX
    Explanations

    images within text and captions or photography descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to images and pictures

    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
    âĵĺ
    -0.79
    indal
    -0.78
    ebus
    -0.77
    iations
    -0.73
    die
    -0.73
    ial
    -0.73
    iated
    -0.72
    iate
    -0.71
    iates
    -0.70
    uctor
    -0.70
    POSITIVE LOGITS
     IMAGES
    1.00
     Shutterstock
    0.79
     Sketch
    0.76
     Images
    0.72
     Features
    0.68
    Video
    0.68
     Thrones
    0.68
    pic
    0.66
    ãĥĭ
    0.66
    Feature
    0.66
    Activations Density 0.066%

    No Known Activations