© 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. 13384
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizations

    oai_token-act-pair · gpt-3.5-turbo

    articles and modifiers associated with countable nouns or references to groups of things

    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
    inside
    -0.74
    isites
    -0.66
    istar
    -0.65
    ··
    -0.62
    Finish
    -0.60
    cu
    -0.60
     engagements
    -0.58
    iev
    -0.58
    ittens
    -0.57
    gre
    -0.56
    POSITIVE LOGITS
     plethora
    1.65
     multitude
    1.62
     lot
    1.53
     variety
    1.51
     handful
    1.47
     number
    1.45
     myriad
    1.43
     slew
    1.41
     bunch
    1.31
     few
    1.25
    Activations Density 0.412%

    No Known Activations