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. 22909
    Prev
    Next
    INDEX
    Explanations

    email addresses with the name "Baxter Holmes"

    oai_token-act-pair · gpt-3.5-turbo

    names and addresses related to characters in a narrative

    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
     eggs
    -0.90
     egg
    -0.87
    Ren
    -0.86
     ank
    -0.83
     membranes
    -0.82
     wings
    -0.81
    egg
    -0.81
     nesting
    -0.79
     Unic
    -0.78
    osph
    -0.78
    POSITIVE LOGITS
     Holmes
    2.40
     Watson
    2.31
     Sherlock
    1.90
    Hol
    1.63
     Mori
    1.61
     Doyle
    1.60
    Sher
    1.53
     Barrett
    1.32
    atson
    1.26
     Conan
    1.24
    Activations Density 0.227%

    No Known Activations