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. 9939
    Prev
    Next
    INDEX
    Explanations

    words related to transportation infrastructure, specifically rail and subway lines

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transportation infrastructure, particularly rail and subway systems

    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
    AppData
    -0.77
    Alien
    -0.64
    Wiki
    -0.64
    idav
    -0.63
     Grass
    -0.63
     unden
    -0.62
    reditary
    -0.62
    sonian
    -0.62
    afort
    -0.62
     embry
    -0.62
    POSITIVE LOGITS
    route
    1.03
     trains
    1.02
     buses
    1.02
     railways
    1.00
     railway
    0.95
     stations
    0.92
    roads
    0.91
     commuters
    0.90
     streetcar
    0.89
    way
    0.89
    Activations Density 0.163%

    No Known Activations