© 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. 7-RES-JB
    6. 2942
    Prev
    Next
    INDEX
    Explanations

    instances where the text expresses an almost emotional or physical reaction

    oai_token-act-pair · gpt-3.5-turbo
    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
    nation
    -0.79
     Dynamics
    -0.75
    Ds
    -0.73
    oran
    -0.71
    voc
    -0.71
    held
    -0.66
    sheet
    -0.65
     UNITED
    -0.65
    ä¸Ń
    -0.65
    ourses
    -0.64
    POSITIVE LOGITS
     certainly
    0.82
     resemble
    0.73
     hypnot
    0.71
    MpServer
    0.69
     like
    0.69
     forgotten
    0.68
     fool
    0.68
     bankrupt
    0.68
     choked
    0.68
     accidentally
    0.68
    Activations Density 0.041%

    No Known Activations