© 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. 6-RES-JB
    11. 17132
    Prev
    Next
    INDEX
    Explanations

    descriptions of sports plays

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports events and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unemploy
    -0.91
    onym
    -0.89
    netflix
    -0.88
    wiki
    -0.84
    enegger
    -0.82
    é¾įå¥ij士
    -0.81
    uminati
    -0.77
    chwitz
    -0.76
    quartered
    -0.76
    zos
    -0.74
    POSITIVE LOGITS
     halftime
    1.02
     score
    1.00
     scorer
    0.89
     scoring
    0.88
     stopp
    0.87
     foul
    0.87
     pounding
    0.85
     frantic
    0.85
     teammate
    0.83
     overpower
    0.83
    Activations Density 0.702%

    No Known Activations