© 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. 17243
    Prev
    Next
    INDEX
    Explanations

    numeric comparisons, such as "more than" or "less than," in the context of quantities or values

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases related to statistical measurements

    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
    binary
    -0.70
    onomy
    -0.70
    content
    -0.68
    iol
    -0.68
    Language
    -0.66
    Blog
    -0.66
    Keys
    -0.66
    rio
    -0.65
    goo
    -0.65
    translation
    -0.65
    POSITIVE LOGITS
    lihood
    0.88
    avorite
    0.80
     comparable
    0.79
     average
    0.74
     any
    0.73
     doubling
    0.73
     expected
    0.72
     what
    0.72
     equivalent
    0.70
     anywhere
    0.70
    Activations Density 0.129%

    No Known Activations