© 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. 11-RES-JB
    11. 22172
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and relative pronouns

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and relative clauses that refer to people or characters

    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
    tnc
    -0.66
    rift
    -0.62
    PLIED
    -0.57
    0200
    -0.56
    ERG
    -0.56
     VIDEOS
    -0.55
    emate
    -0.54
    aukee
    -0.54
    inders
    -0.52
    INST
    -0.52
    POSITIVE LOGITS
     incidentally
    1.41
     admittedly
    1.12
     thankfully
    1.05
     presumably
    1.04
     doubtless
    0.99
     I
    0.98
     fortunately
    0.95
     obviously
    0.93
     sadly
    0.91
     ironically
    0.91
    Activations Density 0.223%

    No Known Activations