© 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. 7-RES-JB
    11. 11128
    Prev
    Next
    INDEX
    Explanations

    comparative words indicating quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative terms relating to quantities and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     NCT
    -0.70
     Clarks
    -0.70
    riad
    -0.68
    Austral
    -0.67
    Fall
    -0.66
    github
    -0.66
     Tray
    -0.63
     ãĤµ
    -0.61
     Lent
    -0.60
     Finder
    -0.59
    POSITIVE LOGITS
     respectively
    0.95
     depending
    0.81
     thereof
    0.81
    lycer
    0.79
    rongh
    0.73
     paced
    0.68
     alike
    0.68
     consecut
    0.68
     apiece
    0.65
     annually
    0.64
    Activations Density 0.045%

    No Known Activations