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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 23582
    Prev
    Next
    INDEX
    Explanations

    team efforts or collaborations in research

    oai_token-act-pair · gpt-3.5-turbo

    references to research teams and collaborative scientific efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.93
    é»Ĵ
    -0.87
    Interstitial
    -0.81
    itol
    -0.79
    vote
    -0.79
    ghazi
    -0.79
    20439
    -0.78
    à¼
    -0.76
    ãĥĸ
    -0.76
    andise
    -0.75
    POSITIVE LOGITS
     researchers
    1.81
     scientists
    1.62
     biologists
    1.55
     archaeologists
    1.50
     physicists
    1.49
     psychologists
    1.48
     astronomers
    1.46
     professors
    1.37
     academics
    1.36
     collaborators
    1.35
    Activations Density 0.266%

    No Known Activations