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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20614
    Prev
    Next
    INDEX
    Explanations

    names (specifically "Ann") in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ann."

    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
    EStreamFrame
    -0.77
     questioning
    -0.70
     Scouting
    -0.70
    xual
    -0.69
    vous
    -0.68
    ierrez
    -0.67
    acters
    -0.66
    raltar
    -0.66
     dare
    -0.64
     ants
    -0.62
    POSITIVE LOGITS
    ihilation
    1.44
    ihil
    1.40
    ouncing
    1.33
    iversary
    1.29
    ounces
    1.28
    apolis
    1.27
    ounced
    1.27
    unciation
    1.26
    abel
    1.24
    abeth
    1.22
    Activations Density 0.021%

    No Known Activations