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. 20770
    Prev
    Next
    INDEX
    Explanations

    proper nouns starting with 'St'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "St." which likely refers to "Street" or "Saint"

    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
    zai
    -0.75
    xus
    -0.73
    hedon
    -0.71
    llah
    -0.70
    omever
    -0.70
    budget
    -0.68
    uchi
    -0.67
    elligence
    -0.65
    #$
    -0.63
    pai
    -0.63
    POSITIVE LOGITS
     St
    3.22
    St
    2.31
     Saint
    1.79
     ST
    1.59
     st
    1.55
    Saint
    1.49
     Ave
    1.38
     STL
    1.32
     Sta
    1.31
     Str
    1.28
    Activations Density 0.016%

    No Known Activations