© 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. 13079
    Prev
    Next
    INDEX
    Explanations

    superlatives or items considered among the best or most significant in their category

    oai_token-act-pair · gpt-3.5-turbo

    references to notable attributes or features of a subject

    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
     Translation
    -0.74
    iture
    -0.74
    ahime
    -0.71
    fulness
    -0.69
    eat
    -0.68
    someone
    -0.67
    ption
    -0.66
    ãĥ³
    -0.64
    eret
    -0.63
    aeus
    -0.63
    POSITIVE LOGITS
     busiest
    1.46
     toughest
    1.39
     hottest
    1.39
     safest
    1.39
     finest
    1.35
     oldest
    1.35
     fastest
    1.33
     poorest
    1.33
     richest
    1.32
     strongest
    1.31
    Activations Density 0.087%

    No Known Activations