© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5392
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of diversity or elements that are varied in nature

    oai_token-act-pair · gpt-3.5-turbo

    references to mixed-use developments or concepts

    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
    debian
    -0.71
    utan
    -0.70
    metic
    -0.70
    WARD
    -0.69
     Annotations
    -0.68
    ond
    -0.67
    si
    -0.67
    ury
    -0.67
    adr
    -0.66
     }}
    -0.66
    POSITIVE LOGITS
     mixed
    0.94
     mixes
    0.83
     Mixed
    0.83
     sexes
    0.77
     mixing
    0.75
    iple
    0.74
     martial
    0.69
     feelings
    0.69
    creen
    0.68
     genders
    0.68
    Activations Density 0.010%

    No Known Activations