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. 24345
    Prev
    Next
    INDEX
    Explanations

    mentions of transportation-related terms, specifically focusing on trains and tunnel-related words

    oai_token-act-pair · gpt-3.5-turbo

    references to trains and transportation-related terms

    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
     Hick
    -0.83
     Carter
    -0.68
    oses
    -0.66
     McGr
    -0.65
    resp
    -0.63
     Barron
    -0.63
     Bates
    -0.63
     Clayton
    -0.62
     Hip
    -0.62
     HB
    -0.62
    POSITIVE LOGITS
    train
    2.98
    tun
    2.06
    odon
    1.23
    TOR
    1.16
    wagen
    1.07
    uner
    1.00
    Train
    1.00
    ENG
    0.97
     Levant
    0.96
    din
    0.95
    Activations Density 0.026%

    No Known Activations