© 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. 3-RES-JB
    11. 542
    Prev
    Next
    INDEX
    Explanations

    exotic or unusual entities, characteristics, or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to exotic or unusual characteristics and items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avering
    -0.78
    uyomi
    -0.76
    arten
    -0.74
    lease
    -0.73
    phasis
    -0.71
    creen
    -0.71
    chens
    -0.71
    ynthesis
    -0.69
    avers
    -0.69
    chen
    -0.68
    POSITIVE LOGITS
    ishly
    1.07
     exotic
    0.93
     dancer
    0.79
     beasts
    0.77
     outl
    0.74
     destinations
    0.71
     talents
    0.70
     pets
    0.69
     tropical
    0.69
     affairs
    0.68
    Activations Density 0.011%

    No Known Activations