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. 11-RES-JB
    6. 10734
    Prev
    Next
    INDEX
    Explanations

    the name "Mary" with varying levels of significance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mary."

    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
    */(
    -0.73
    cffff
    -0.72
     deported
    -0.64
     obstruction
    -0.63
     nationals
    -0.63
     racial
    -0.63
    ickr
    -0.62
    chnology
    -0.61
    ious
    -0.61
     untreated
    -0.60
    POSITIVE LOGITS
    anne
    1.17
    lene
    1.16
     Jane
    1.10
     Ellen
    1.07
    Anne
    1.07
    Kay
    1.05
     Beth
    1.03
     Anne
    1.00
    Jane
    1.00
    ellen
    0.99
    Activations Density 0.027%

    No Known Activations