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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 16367
    Prev
    Next
    INDEX
    Explanations

    copyright information for images

    oai_token-act-pair · gpt-3.5-turbo

    instances of image captions

    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
     Sapp
    -0.76
    20439
    -0.67
     reconc
    -0.66
    rats
    -0.66
     Genie
    -0.63
    ij士
    -0.63
    comed
    -0.61
     Adin
    -0.61
    nen
    -0.60
     nodd
    -0.60
    POSITIVE LOGITS
     caption
    1.66
     copyright
    1.00
     Image
    0.87
     Gallery
    0.82
     Images
    0.81
    Image
    0.79
    imedia
    0.74
     image
    0.74
     gallery
    0.72
     URL
    0.72
    Activations Density 0.008%

    No Known Activations