© 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. 8-RES-JB
    11. 3296
    Prev
    Next
    INDEX
    Explanations

    television shows or programs that are being aired or have been aired

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to television programming, specifically about shows that are aired

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    llan
    -0.77
     Templ
    -0.67
     Cust
    -0.65
    ansson
    -0.64
     slippery
    -0.63
    acqu
    -0.63
     Prompt
    -0.62
    ortium
    -0.61
    ulkan
    -0.60
     Fraz
    -0.59
    POSITIVE LOGITS
     airing
    1.02
    ONY
    1.01
     aired
    0.95
    waves
    0.90
    NPR
    0.84
    episode
    0.83
     Sundays
    0.82
    ONSORED
    0.82
    TIME
    0.80
    caster
    0.79
    Activations Density 0.057%

    No Known Activations