© 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. 1-RES-JB
    11. 6447
    Prev
    Next
    INDEX
    Explanations

    references to television or TV-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to television

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cule
    -0.70
    hot
    -0.70
    htaking
    -0.69
     lazy
    -0.65
     heck
    -0.63
    period
    -0.62
    ãĥĦ
    -0.62
    cific
    -0.60
    vasive
    -0.60
    20439
    -0.60
    POSITIVE LOGITS
    TV
    1.13
    ILLE
    1.10
    iolet
    0.97
    ihar
    0.87
    NG
    0.85
    levision
    0.85
    atcher
    0.83
    NZ
    0.82
    trop
    0.79
     Everywhere
    0.79
    Activations Density 0.007%

    No Known Activations