© 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. 7-RES-JB
    11. 2289
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantity or estimates

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "many" to indicate quantities or large numbers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Brav
    -0.73
     Veil
    -0.66
    agher
    -0.65
    ĺħ
    -0.62
    maxwell
    -0.62
     Powered
    -0.61
    Ļ½
    -0.61
    ardo
    -0.60
     Butterfly
    -0.59
    lance
    -0.59
    POSITIVE LOGITS
    azi
    0.68
     KN
    0.66
     AS
    0.63
    antz
    0.63
    assian
    0.62
    theless
    0.61
     copies
    0.61
     digits
    0.61
     Than
    0.60
    ongh
    0.60
    Activations Density 0.034%

    No Known Activations