© 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. 0-RES-JB
    11. 9820
    Prev
    Next
    INDEX
    Explanations

    news or information related to watching something, such as videos or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to watching or viewing content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     common
    -0.66
     quart
    -0.66
     spelling
    -0.65
     diluted
    -0.63
     conditional
    -0.62
     NON
    -0.62
     inclusive
    -0.62
     ending
    -0.61
     routed
    -0.61
     arg
    -0.60
    POSITIVE LOGITS
    Watch
    3.83
    watch
    2.54
     Watch
    2.48
    WATCH
    2.21
     WATCH
    1.86
     watch
    1.76
    watching
    1.66
    Listen
    1.59
     Watching
    1.55
    Check
    1.37
    Activations Density 0.020%

    No Known Activations