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. 22020
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations, specifically ones containing "Sul"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Sul" and related proper nouns likely associated with entities in maritime or shipping contexts

    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
     Mao
    -0.77
    akings
    -0.69
     HIT
    -0.68
    JJ
    -0.68
     Leviathan
    -0.68
    ÅĤ
    -0.67
     Ortiz
    -0.67
    obl
    -0.67
     Pandora
    -0.66
    arrell
    -0.66
    POSITIVE LOGITS
     Sul
    3.61
    ptroller
    1.49
     squirrel
    1.25
     sulph
    1.18
    mag
    1.16
     sul
    1.14
     Dul
    1.08
     Squirrel
    1.04
     Gum
    1.04
     Thur
    1.02
    Activations Density 0.061%

    No Known Activations