© 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. 10-RES-JB
    11. 11544
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "the story of" or "tells the story of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference narratives or stories about individuals or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reau
    -0.89
    hement
    -0.79
    soever
    -0.72
    RELATED
    -0.72
    ©¶æ¥µ
    -0.71
    ews
    -0.70
    provided
    -0.70
    cially
    -0.69
    oreal
    -0.69
    HEAD
    -0.69
    POSITIVE LOGITS
     how
    1.18
     why
    0.95
     heroism
    0.92
     overcoming
    0.82
     persever
    0.79
     HOW
    0.78
     mankind
    0.75
     Edwin
    0.73
     How
    0.72
     Jonah
    0.72
    Activations Density 0.191%

    No Known Activations