© 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. 13887
    Prev
    Next
    INDEX
    Explanations

    mentions of specific dates and various names or terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and geographic locations

    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
     eleph
    -1.17
    ©¶æ
    -1.04
     exting
    -0.94
     practition
    -0.94
     teasp
    -0.94
    Þ
    -0.93
    Ý
    -0.93
    ñ
    -0.92
     pione
    -0.91
     unnecess
    -0.90
    POSITIVE LOGITS
    o
    1.25
    e
    1.17
    a
    1.12
    u
    1.04
    i
    1.01
    y
    1.01
    oS
    0.98
    aq
    0.98
    an
    0.96
    ean
    0.93
    Activations Density 0.169%

    No Known Activations