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. 2-RES-JB
    6. 3815
    Prev
    Next
    INDEX
    Explanations

    words related to brackets or categorization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bracket" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.68
     Soy
    -0.66
    ternity
    -0.63
    uv
    -0.63
    BuyableInstoreAndOnline
    -0.60
     Traffic
    -0.59
    BLIC
    -0.59
     Antar
    -0.59
     Republic
    -0.57
    ULT
    -0.57
    POSITIVE LOGITS
     brackets
    1.33
     bracket
    1.30
    ackets
    1.16
    acket
    1.01
    halla
    0.75
    ashtra
    0.75
    cake
    0.73
    ftime
    0.71
    alon
    0.71
    olson
    0.70
    Activations Density 0.013%

    No Known Activations