© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 13960
    Prev
    Next
    INDEX
    Explanations

    phrases related to online videos

    oai_token-act-pair · gpt-3.5-turbo

    references to videos, particularly within the context of content sharing and commentary

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptive
    -0.66
    å§«
    -0.65
     Dew
    -0.63
     leukemia
    -0.62
     guess
    -0.62
    idate
    -0.61
     wedge
    -0.60
    ppo
    -0.59
    phant
    -0.59
     Newark
    -0.59
    POSITIVE LOGITS
     videos
    1.11
    ynthesis
    1.05
     uploaded
    0.95
    hops
    0.94
     Videos
    0.93
    uploads
    0.92
    videos
    0.89
     tutorials
    0.86
    quished
    0.85
     Thumbnails
    0.83
    Activations Density 0.013%

    No Known Activations