© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24073
    Prev
    Next
    INDEX
    Explanations

    comparisons or examples with the word "too" or indicating similarity/duality

    oai_token-act-pair · gpt-3.5-turbo

    the recurring phrase "too" in various contexts

    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
     thous
    -0.70
     Versus
    -0.68
     Mansion
    -0.68
     equivalents
    -0.67
    ories
    -0.66
    zan
    -0.66
    bp
    -0.64
    Hy
    -0.63
     '[
    -0.63
    rarily
    -0.62
    POSITIVE LOGITS
     sidx
    0.85
    liga
    0.72
    utenberg
    0.72
    otton
    0.71
    este
    0.69
    vous
    0.68
     besides
    0.64
    iffe
    0.63
    ivably
    0.62
    elvet
    0.62
    Activations Density 0.052%

    No Known Activations