© 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 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. 3-RES-JB
    11. 175
    Prev
    Next
    INDEX
    Explanations

    the name "Nar" with different varying activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of particular individuals or characters within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AQ
    -0.77
     Purg
    -0.75
    ences
    -0.73
    perture
    -0.72
    ITNESS
    -0.72
     Extrem
    -0.71
     Pixie
    -0.71
     UID
    -0.71
    UID
    -0.70
    Rare
    -0.68
    POSITIVE LOGITS
    nar
    1.04
    kees
    1.01
    illion
    0.88
    sson
    0.86
    negie
    0.85
    zynski
    0.85
    iola
    0.83
    stan
    0.83
    vik
    0.81
    ussian
    0.81
    Activations Density 0.006%

    No Known Activations