© 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. 4924
    Prev
    Next
    INDEX
    Explanations

    references to "Otter" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific type of animal, particularly otters

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    Ùħ
    -0.74
    behavior
    -0.71
    advertisement
    -0.71
     Cambodia
    -0.69
    âĸ¬
    -0.69
    arthy
    -0.67
    $$$$
    -0.66
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
     Effective
    -0.64
    POSITIVE LOGITS
     Ot
    1.21
    terness
    1.21
     ot
    0.96
    ago
    0.96
    itles
    0.95
    hei
    0.95
    aku
    0.95
    oga
    0.93
    olith
    0.93
    ocol
    0.93
    Activations Density 0.006%

    No Known Activations