Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 87
    Prev
    Next
    INDEX
    Explanations

    captions in an image gallery

    oai_token-act-pair · gpt-3.5-turbo

    image captions and related textual elements

    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
     unsett
    -0.79
    etheless
    -0.77
     concussion
    -0.74
     peanuts
    -0.73
     knees
    -0.73
     incorpor
    -0.71
    bats
    -0.70
    metic
    -0.68
     oath
    -0.68
    shake
    -0.68
    POSITIVE LOGITS
     Courtesy
    1.43
    Courtesy
    1.02
     COURT
    1.01
     Shutterstock
    0.97
     Image
    0.92
     REUTERS
    0.91
     ©
    0.90
     toggle
    0.89
     Provided
    0.89
     Photograph
    0.89
    Activations Density 0.010%

    No Known Activations