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. 3-RES-JB
    6. 22508
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "urs" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "urs" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clarkson
    -0.72
     booth
    -0.68
     Tunis
    -0.62
     LU
    -0.60
    Bey
    -0.60
     rob
    -0.60
     Metatron
    -0.59
     machine
    -0.59
     Ik
    -0.58
     Mell
    -0.58
    POSITIVE LOGITS
    hip
    1.18
    uits
    1.14
    uit
    1.07
    atile
    1.04
    ury
    1.04
    urs
    1.02
     confir
    1.00
    orrow
    0.98
    geons
    0.97
    ensical
    0.91
    Activations Density 0.005%

    No Known Activations