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. 10-RES-JB
    6. 22061
    Prev
    Next
    INDEX
    Explanations

    phrases or words containing the substring "se."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "se" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.70
     Banner
    -0.65
    initely
    -0.64
    ington
    -0.62
     hoops
    -0.62
     Vector
    -0.60
    SHIP
    -0.59
     Gim
    -0.59
     Union
    -0.59
     Hos
    -0.58
    POSITIVE LOGITS
    ptic
    1.20
    ldom
    1.17
    xt
    1.17
    perate
    1.16
    gue
    1.16
    pt
    1.12
    eps
    1.10
    xton
    1.08
    ep
    1.07
    rene
    1.06
    Activations Density 0.015%

    No Known Activations