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. 11-RES-JB
    6. 4679
    Prev
    Next
    INDEX
    Explanations

    text related to political figures and actions

    oai_token-act-pair · gpt-3.5-turbo
    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
    Moore
    -0.97
    heed
    -0.83
     Kaw
    -0.78
     awa
    -0.76
    Oak
    -0.76
    ayne
    -0.75
     Booker
    -0.74
     McKenzie
    -0.74
     NRL
    -0.74
    Carter
    -0.74
    POSITIVE LOGITS
     Hungary
    2.43
     Budapest
    2.41
     Hungarian
    2.39
    Hung
    2.08
     Hung
    2.02
     Romania
    1.91
     Romanian
    1.84
     Slovakia
    1.77
     Bulgar
    1.72
     Viktor
    1.68
    Activations Density 0.178%

    No Known Activations