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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 16004
    Prev
    Next
    INDEX
    Explanations

    references to sports events such as games and matches

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports events and match fixtures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Wiki
    -0.70
     Prism
    -0.66
    aft
    -0.64
    acea
    -0.63
     Expression
    -0.61
    achev
    -0.61
    urat
    -0.61
    nda
    -0.60
     Spears
    -0.60
    hari
    -0.59
    POSITIVE LOGITS
     opener
    1.02
     postponed
    1.01
     scheduled
    1.00
     televised
    0.96
     scheduling
    0.93
     schedule
    0.92
     against
    0.90
    Tickets
    0.87
     matchup
    0.87
     airs
    0.86
    Activations Density 0.168%

    No Known Activations