© 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. 3636
    Prev
    Next
    INDEX
    Explanations

    references to specific types of seals, particularly the "elephant seal."

    oai_token-act-pair · gpt-3.5-turbo

    references to different species of seals

    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
    itters
    -0.73
    enegger
    -0.69
    chy
    -0.67
    orne
    -0.67
     Ort
    -0.66
    schild
    -0.66
     Drawn
    -0.66
     Rove
    -0.63
    cart
    -0.62
     Lov
    -0.62
    POSITIVE LOGITS
     seal
    1.35
     seals
    1.24
     sealing
    0.96
     Seal
    0.89
    ife
    0.87
    keeper
    0.79
    heed
    0.78
    wrap
    0.75
    ldom
    0.75
     oath
    0.72
    Activations Density 0.007%

    No Known Activations