© 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. 10395
    Prev
    Next
    INDEX
    Explanations

    the word "Logan"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Logan" and "Wolverine."

    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
    haps
    -0.89
    ktop
    -0.86
    placed
    -0.83
    minist
    -0.81
    tops
    -0.80
    bid
    -0.79
    ramid
    -0.77
     pse
    -0.73
    Prev
    -0.72
    fix
    -0.71
    POSITIVE LOGITS
     Logan
    1.48
     Lucky
    0.81
     Dull
    0.79
    ogan
    0.78
     Cable
    0.76
     airport
    0.75
     Seal
    0.74
     Salmon
    0.74
     Skywalker
    0.73
    loo
    0.73
    Activations Density 0.007%

    No Known Activations