© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 14889
    Prev
    Next
    INDEX
    Explanations

    instances of the word "watch" followed by some action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to watching videos or live broadcasts

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

    No Comments

    Negative Logits
    insula
    -0.71
    wx
    -0.66
     Syl
    -0.66
    rette
    -0.65
    illet
    -0.65
     reusable
    -0.65
    omorphic
    -0.63
    ascal
    -0.63
    isma
    -0.62
     âĵĺ
    -0.62
    POSITIVE LOGITS
     VIDEOS
    1.05
     unfold
    0.99
    flix
    0.83
    ideos
    0.80
     broadcasts
    0.78
     tapes
    0.77
    runs
    0.75
     cartoons
    0.75
     videos
    0.74
     films
    0.72
    Activations Density 0.140%

    No Known Activations