© 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. 9-RES-JB
    11. 3249
    Prev
    Next
    INDEX
    Explanations

    economic and demographic statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to demographics and economic metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aud
    -0.68
    iate
    -0.63
    iates
    -0.60
    elight
    -0.59
     interactions
    -0.58
    boxes
    -0.57
     tabs
    -0.57
    waves
    -0.57
     EDITION
    -0.56
    minster
    -0.55
    POSITIVE LOGITS
     exceeding
    1.30
     ranging
    1.29
     totaling
    1.05
     comparable
    0.97
     averaging
    0.95
     spanning
    0.92
     resembling
    0.90
    ranging
    0.89
     âī¥
    0.89
     approx
    0.89
    Activations Density 0.222%

    No Known Activations