© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 20211
    Prev
    Next
    INDEX
    Explanations

    types of objects described in scientific or technical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to artistic concepts and representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     veter
    -0.76
     squads
    -0.72
     counselors
    -0.70
     pse
    -0.69
     boycot
    -0.67
     advis
    -0.67
     specials
    -0.67
     electing
    -0.67
     appointing
    -0.66
    lear
    -0.66
    POSITIVE LOGITS
     Photograph
    1.78
     Photo
    1.49
     Image
    1.48
     Credit
    1.46
     Courtesy
    1.46
     Wikimedia
    1.40
     Picture
    1.39
     Illust
    1.38
     PHOTO
    1.36
     Shutterstock
    1.34
    Activations Density 0.191%

    No Known Activations