© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    verbs related to the act of physically reaching a destination

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "arrive" and its variations

    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
    uyomi
    -0.72
     )]
    -0.66
    ĸļ
    -0.66
     Principle
    -0.66
    ©¶æ
    -0.64
    Series
    -0.64
     Mahjong
    -0.64
    oggle
    -0.62
     Parables
    -0.61
    addy
    -0.61
    POSITIVE LOGITS
     safely
    0.94
     aboard
    0.84
     home
    0.83
     at
    0.80
     ashore
    0.77
     onboard
    0.76
     shores
    0.73
    cation
    0.73
     victorious
    0.70
     here
    0.70
    Activations Density 0.073%

    No Known Activations