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. 6-RES-JB
    6. 1413
    Prev
    Next
    INDEX
    Explanations

    mentions of buildings

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of specific buildings, particularly focusing on "building 9" and "building 8."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opard
    -0.88
    romeda
    -0.85
    nir
    -0.84
    sha
    -0.78
    ï¸ı
    -0.77
    ican
    -0.73
    ricular
    -0.73
    uel
    -0.73
    flix
    -0.71
     Nadu
    -0.71
    POSITIVE LOGITS
    raper
    0.97
     blocks
    0.96
     renovations
    0.96
     occupancy
    0.93
    building
    0.86
     buildings
    0.86
     constructed
    0.85
     erected
    0.85
     renovation
    0.82
     entrances
    0.82
    Activations Density 0.029%

    No Known Activations