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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 11-RES-JB
    6. 10845
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms related to the state of Minnesota

    oai_token-act-pair · gpt-3.5-turbo

    references to government actions or decisions related to Minnesota

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BAT
    -1.22
    Batman
    -1.20
    BAT
    -1.06
    Bat
    -1.05
    bat
    -1.02
    Catal
    -1.00
     bat
    -0.98
     Britann
    -0.96
    Spain
    -0.96
     Batman
    -0.95
    POSITIVE LOGITS
    Minnesota
    2.29
     Minnesota
    2.25
     Minneapolis
    2.06
     MN
    1.94
     Vikings
    1.77
     Timberwolves
    1.67
    MN
    1.64
    neapolis
    1.54
     Twin
    1.49
     Dul
    1.48
    Activations Density 0.174%

    No Known Activations