© 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. 4-RES-JB
    11. 24395
    Prev
    Next
    INDEX
    Explanations

    video-related tokens

    oai_token-act-pair · gpt-3.5-turbo

    parts of text that indicate video content or references to videos

    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
    heit
    -1.11
    ahime
    -0.88
     laure
    -0.85
    luster
    -0.74
    wit
    -0.73
     Pact
    -0.72
    hirt
    -0.70
     reins
    -0.66
    ktop
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    POSITIVE LOGITS
     Videos
    0.90
     Video
    0.87
    YouTube
    0.86
     uploaded
    0.86
     upload
    0.84
    ideos
    0.83
     Youtube
    0.83
    Video
    0.82
     youtube
    0.80
     YouTube
    0.80
    Activations Density 0.244%

    No Known Activations