© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8480
    Prev
    Next
    INDEX
    Explanations

    companies, industries, and entities related to different sectors of the economy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ription
    -0.62
    aeper
    -0.61
    ython
    -0.61
    lished
    -0.61
    atown
    -0.59
    acion
    -0.58
    senal
    -0.57
    icum
    -0.57
    regon
    -0.57
    yden
    -0.55
    POSITIVE LOGITS
     EVER
    0.98
     Ever
    0.84
     ever
    0.79
    —
    0.76
     imaginable
    0.75
    Ever
    0.75
    ,,
    0.69
    mith
    0.67
    ever
    0.67
    liner
    0.67
    Activations Density 0.244%

    No Known Activations