© 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 EvalsExportsinterp-engineNEWAPI 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. 11521
    Prev
    Next
    INDEX
    Explanations

    the action of watching or looking at something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "watch" and its variations

    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
    esan
    -0.85
    ãĥ´
    -0.85
    interstitial
    -0.73
    wealth
    -0.73
    eno
    -0.70
    enture
    -0.70
    enos
    -0.67
    phi
    -0.66
    orrect
    -0.66
    bole
    -0.64
    POSITIVE LOGITS
    dogs
    1.15
    dog
    1.06
    tower
    0.97
     helpless
    0.96
     Watching
    0.93
     tv
    0.90
     videos
    0.89
     closely
    0.85
     TV
    0.85
     watching
    0.83
    Activations Density 0.039%

    No Known Activations