© 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. 12630
    Prev
    Next
    INDEX
    Explanations

    numerical measurements such as quantities or dimensions

    oai_token-act-pair · gpt-3.5-turbo

    numbers and statistics related to votes, measurements, and quantities

    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
     Faul
    -0.67
     Coch
    -0.62
    sell
    -0.58
    brand
    -0.57
     Belg
    -0.57
     ag
    -0.56
    verty
    -0.56
    roup
    -0.55
     Sebast
    -0.55
    dq
    -0.55
    POSITIVE LOGITS
    %-
    0.73
     yen
    0.72
    utenberg
    0.70
    âĢ²
    0.69
    mm
    0.69
    ecause
    0.68
    itialized
    0.68
    ½
    0.68
    ÃĹ
    0.68
     consecutive
    0.67
    Activations Density 0.171%

    No Known Activations