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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21718
    Prev
    Next
    INDEX
    Explanations

    references to the United Kingdom (U.K.)

    oai_token-act-pair · gpt-3.5-turbo

    references to the UK as a significant geographical or political entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rods
    -0.80
    sys
    -0.63
     fractures
    -0.60
     packets
    -0.59
    в
    -0.58
     cozy
    -0.57
    quickShipAvailable
    -0.57
     wee
    -0.57
    éĹĺ
    -0.57
    ãĥŀ
    -0.57
    POSITIVE LOGITS
    istani
    1.14
    orea
    0.81
    erning
    0.79
    ernel
    0.77
    DOM
    0.77
    ruck
    0.75
    orean
    0.75
     Embassy
    0.75
    owitz
    0.75
     Isles
    0.73
    Activations Density 0.014%

    No Known Activations