© 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. 6-RES-JB
    11. 11983
    Prev
    Next
    INDEX
    Explanations

    video-related terms and cues to prompt viewers to watch

    oai_token-act-pair · gpt-3.5-turbo

    references to video content and sharing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recl
    -0.66
     reconciliation
    -0.63
     libel
    -0.60
     academia
    -0.60
    Ļ½
    -0.60
    umped
    -0.58
    sole
    -0.58
     Galile
    -0.57
     diss
    -0.57
     Sap
    -0.57
    POSITIVE LOGITS
     Videos
    1.07
     Thumbnails
    1.04
     WATCHED
    0.89
     âĢº
    0.84
     VIDEOS
    0.83
    iques
    0.82
    icult
    0.78
    Video
    0.76
     Loading
    0.71
     Video
    0.70
    Activations Density 0.008%

    No Known Activations