© 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. 17182
    Prev
    Next
    INDEX
    Explanations

    phrases indicating that something should be interpreted in a particular way

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "viewed" and its related context

    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
    ften
    -0.72
    backer
    -0.70
    nown
    -0.63
    ammy
    -0.61
    weather
    -0.61
    vous
    -0.60
    breaker
    -0.60
     Laurent
    -0.59
    yan
    -0.59
    cover
    -0.59
    POSITIVE LOGITS
    ById
    0.99
    phas
    0.83
    æѦ
    0.79
     favorably
    0.79
    ĸ
    0.77
    ª
    0.76
    æĦ
    0.75
    ASED
    0.74
    isions
    0.74
    Ĺ
    0.73
    Activations Density 0.044%

    No Known Activations