© 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. 1-RES-JB
    11. 3755
    Prev
    Next
    INDEX
    Explanations

    references to a specific title or term 'Legend'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Legend" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chy
    -0.68
     behalf
    -0.66
    ters
    -0.65
    Interstitial
    -0.64
    imentary
    -0.63
    ted
    -0.62
    erry
    -0.62
    ushing
    -0.61
    berra
    -0.60
     stark
    -0.60
    POSITIVE LOGITS
     Legend
    1.28
    Legend
    1.15
    uin
    0.88
    naire
    0.82
     Tales
    0.78
    lore
    0.77
     legend
    0.74
     Chaser
    0.74
     Cous
    0.71
     Tale
    0.70
    Activations Density 0.005%

    No Known Activations