© 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. 10032
    Prev
    Next
    INDEX
    Explanations

    references to the character "Captain America" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Captain America

    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
    ucl
    -0.67
     exch
    -0.67
    numbered
    -0.67
    ocene
    -0.66
    itual
    -0.64
    Neigh
    -0.64
    tsy
    -0.60
    upon
    -0.60
    aeda
    -0.60
    choice
    -0.59
    POSITIVE LOGITS
    cy
    1.17
    cies
    0.98
    esses
    0.91
     Kidd
    0.86
    berries
    0.84
     Picard
    0.80
    istics
    0.77
     Phillips
    0.76
    berry
    0.76
    ials
    0.74
    Activations Density 0.031%

    No Known Activations