© 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. 10-RES-JB
    11. 10086
    Prev
    Next
    INDEX
    Explanations

    words related to travel destinations and community-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to travel and destinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abl
    -0.84
    abouts
    -0.78
    cephal
    -0.74
    ety
    -0.73
    asel
    -0.72
    rums
    -0.70
    leigh
    -0.69
    furt
    -0.69
    rex
    -0.69
    hend
    -0.68
    POSITIVE LOGITS
     Flavoring
    0.78
    culosis
    0.70
    dayName
    0.68
    èĢħ
    0.67
     categorized
    0.66
    Magazine
    0.63
    ividual
    0.63
    thinkable
    0.62
    Movie
    0.62
    ategor
    0.62
    Activations Density 0.060%

    No Known Activations