© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14744
    Prev
    Next
    INDEX
    Explanations

    medical terms and codes

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or symbols related to medical or scientific data

    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
    gas
    -0.81
    ante
    -0.73
    usat
    -0.71
    credit
    -0.67
    ãĥ«
    -0.64
    iris
    -0.64
    aris
    -0.64
    cars
    -0.64
    jas
    -0.64
    emi
    -0.64
    POSITIVE LOGITS
    senal
    0.69
     stray
    0.66
     Leilan
    0.66
    sterdam
    0.62
    ĸļ
    0.61
    ĺħ
    0.61
    nesday
    0.60
     existed
    0.57
     perished
    0.56
    imately
    0.56
    Activations Density 0.329%

    No Known Activations