© 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. 1930
    Prev
    Next
    INDEX
    Explanations

    live broadcasting events on television or online

    oai_token-act-pair · gpt-3.5-turbo

    mentions of live televised events

    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
    ndra
    -1.05
    ework
    -0.83
    ebus
    -0.82
    esters
    -0.74
    etsy
    -0.74
    ealous
    -0.74
    selage
    -0.72
    weak
    -0.72
    aez
    -0.69
    zanne
    -0.69
    POSITIVE LOGITS
     broadcasts
    1.34
     telev
    1.32
     broadcast
    1.28
     televised
    1.23
     broadcasting
    1.20
    ESPN
    1.17
    TV
    1.16
     broadcasters
    1.12
     television
    1.12
     simul
    1.12
    Activations Density 0.404%

    No Known Activations