© 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. 7518
    Prev
    Next
    INDEX
    Explanations

    phrases related to proving or demonstrating something

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to talent or skill recognition

    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
     References
    -0.64
     Rape
    -0.62
    stab
    -0.62
     Lent
    -0.59
     raping
    -0.58
    intensive
    -0.57
    stocks
    -0.57
     Edited
    -0.56
    lihood
    -0.56
    figure
    -0.55
    POSITIVE LOGITS
     accordingly
    0.95
     exception
    0.84
     remedy
    0.74
    empl
    0.73
    olk
    0.73
     such
    0.72
    example
    0.72
    Thankfully
    0.69
    burgh
    0.69
    AMI
    0.69
    Activations Density 1.110%

    No Known Activations