© 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. 20432
    Prev
    Next
    INDEX
    Explanations

    phrases indicating storytelling or sharing information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize direct communication or statements directed at someone

    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
    hement
    -0.59
    ©¶æ¥µ
    -0.59
    iw
    -0.59
    hift
    -0.58
    luster
    -0.55
    osp
    -0.54
    untarily
    -0.54
     recourse
    -0.53
    ibly
    -0.53
    calling
    -0.53
    POSITIVE LOGITS
     guys
    1.24
     somet
    0.87
     anecd
    0.80
     why
    0.78
     yourselves
    0.77
    're
    0.75
     firsthand
    0.75
     something
    0.73
     bluntly
    0.71
     dudes
    0.70
    Activations Density 0.029%

    No Known Activations