© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 20358
    Prev
    Next
    INDEX
    Explanations

    words related to sports events and news

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events and their details

    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
     fundra
    -0.68
     NGO
    -0.67
     Soros
    -0.66
     mobil
    -0.66
     NGOs
    -0.65
     populist
    -0.61
     locality
    -0.61
     constituency
    -0.61
     subsistence
    -0.61
     interf
    -0.61
    POSITIVE LOGITS
    NBA
    1.37
    ESPN
    1.37
    NFL
    1.28
    Football
    1.25
    ichick
    1.25
    football
    1.20
     NFL
    1.17
     ESPN
    1.12
    Sports
    1.12
     FANTASY
    1.10
    Activations Density 0.180%

    No Known Activations