© 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. 0-RES-JB
    11. 12044
    Prev
    Next
    INDEX
    Explanations

    references to different types of large cats, particularly lions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of lions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ettings
    -0.79
     UD
    -0.71
    Settings
    -0.65
     Disp
    -0.64
    space
    -0.63
     Minutes
    -0.63
     Deg
    -0.62
     Coff
    -0.62
    aps
    -0.62
    ession
    -0.62
    POSITIVE LOGITS
     lion
    3.95
     lions
    2.90
     Lion
    1.89
     tiger
    1.66
     gorilla
    1.65
     elephant
    1.36
     lamb
    1.32
     tigers
    1.31
     Lions
    1.21
     wolf
    1.21
    Activations Density 0.022%

    No Known Activations