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. 1-RES-JB
    6. 17717
    Prev
    Next
    INDEX
    Explanations

    names containing the string "ab"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sandy
    -0.73
    FTWARE
    -0.72
     Dare
    -0.69
     Maker
    -0.69
     Titanic
    -0.67
     Honour
    -0.67
     Yin
    -0.66
     nomine
    -0.66
     CIS
    -0.65
     order
    -0.63
    POSITIVE LOGITS
    stract
    1.37
    ab
    1.24
    raham
    1.21
    raid
    1.12
    ilib
    1.08
    olics
    1.08
    iotics
    1.06
    uilding
    1.04
    rax
    1.00
    dullah
    0.99
    Activations Density 0.015%

    No Known Activations