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. 735
    Prev
    Next
    INDEX
    Explanations

    keywords related to rail transportation and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    references to rail-related topics

    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
    mony
    -0.74
    uid
    -0.73
    INESS
    -0.72
     Flowers
    -0.71
    Ec
    -0.70
     iTunes
    -0.69
     Choi
    -0.69
    una
    -0.67
    Eth
    -0.67
     Cookies
    -0.66
    POSITIVE LOGITS
     rail
    3.76
    rail
    2.70
     Rail
    2.67
     rails
    2.63
    Rail
    2.59
     railroad
    2.07
     railways
    2.05
     railway
    1.98
     railing
    1.71
     Railway
    1.71
    Activations Density 0.014%

    No Known Activations