© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21179
    Prev
    Next
    INDEX
    Explanations

    superlatives and comparisons related to statistics and rankings

    oai_token-act-pair · gpt-3.5-turbo

    statistical information related to prescriptions and rates across different regions or populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cgi
    -0.75
    eele
    -0.74
    ariat
    -0.66
    oire
    -0.63
    unity
    -0.62
    icz
    -0.59
    acy
    -0.58
    swer
    -0.58
    ries
    -0.58
    icing
    -0.58
    POSITIVE LOGITS
     lowest
    1.50
     highest
    1.49
    highest
    1.34
     widest
    1.25
     fastest
    1.22
     smallest
    1.21
     worst
    1.19
     longest
    1.19
     heaviest
    1.19
     largest
    1.18
    Activations Density 0.156%

    No Known Activations