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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 8986
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically the name "Brownstein."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person, likely in a legal or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pat
    -0.66
     cre
    -0.66
     Rapt
    -0.66
     Religious
    -0.63
     buzz
    -0.61
     crop
    -0.61
     bus
    -0.60
     future
    -0.58
     pale
    -0.58
     motor
    -0.58
    POSITIVE LOGITS
    stein
    4.77
    stadt
    1.40
    berg
    1.34
    wald
    1.34
    tein
    1.33
    enegger
    1.32
    heit
    1.32
    steen
    1.31
    enstein
    1.30
    baum
    1.27
    Activations Density 0.012%

    No Known Activations