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. 10833
    Prev
    Next
    INDEX
    Explanations

    locations where individuals were born

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "born" and associated phrases indicating a person's birthplace

    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
    Cooldown
    -0.82
     certs
    -0.80
    awatts
    -0.77
    doms
    -0.76
    xual
    -0.74
    inventoryQuantity
    -0.70
    Ultimate
    -0.70
    fights
    -0.70
    itized
    -0.69
    sers
    -0.68
    POSITIVE LOGITS
     1946
    1.26
     1952
    1.19
     1947
    1.19
     1948
    1.18
     Jamaica
    1.18
     1924
    1.16
     1928
    1.16
     1961
    1.15
     1951
    1.14
     Kenya
    1.14
    Activations Density 0.073%

    No Known Activations