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. 14432
    Prev
    Next
    INDEX
    Explanations

    words related to buildings and structures

    oai_token-act-pair · gpt-3.5-turbo

    references to physical structures or architectural elements

    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
    pas
    -0.67
    nn
    -0.67
     Grimes
    -0.66
    î
    -0.63
    lah
    -0.63
    Sah
    -0.62
    ALSE
    -0.61
    licks
    -0.60
    Ä«
    -0.59
    submit
    -0.59
    POSITIVE LOGITS
     building
    3.57
     Building
    2.74
    Building
    2.51
    building
    2.49
     buildings
    1.94
     constructing
    1.75
     rebuilding
    1.66
     Buildings
    1.63
     build
    1.61
     builders
    1.54
    Activations Density 0.023%

    No Known Activations