Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5601
    Prev
    Next
    INDEX
    Explanations

    mentions of locations specifically related to the state of Colorado

    oai_token-act-pair · gpt-3.5-turbo

    references to Colorado

    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
    aid
    -0.78
    hap
    -0.76
    eki
    -0.75
     rom
    -0.73
    æĪ¦
    -0.70
    ilib
    -0.69
    fff
    -0.69
    âĶĢâĶĢ
    -0.68
     tun
    -0.67
    Shin
    -0.67
    POSITIVE LOGITS
     Colorado
    3.54
    Colorado
    3.38
     Colo
    2.43
     Denver
    2.29
    Denver
    2.24
     Connecticut
    2.05
     Rockies
    2.04
     Arizona
    2.02
     Boulder
    1.98
     Wyoming
    1.88
    Activations Density 0.015%

    No Known Activations