© 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. 3-RES-JB
    11. 9771
    Prev
    Next
    INDEX
    Explanations

    instances of actions described as being watched

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the act of watching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctrl
    -0.82
    interstitial
    -0.76
    esan
    -0.73
    bole
    -0.70
    orrect
    -0.69
    uria
    -0.69
    ality
    -0.69
    ascal
    -0.69
    emia
    -0.68
    phi
    -0.68
    POSITIVE LOGITS
     Watching
    1.26
     watching
    1.08
     watched
    0.99
    tower
    0.97
    dogs
    0.89
    ÃįÃį
    0.87
     watch
    0.84
     Watch
    0.81
    watching
    0.81
     Wat
    0.78
    Activations Density 0.022%

    No Known Activations