© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18855
    Prev
    Next
    INDEX
    Explanations

    words related to being reasonable or appropriateness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of being reasonable

    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
    skirts
    -0.67
     Variant
    -0.66
    Shape
    -0.62
    sten
    -0.62
    pictured
    -0.61
     =====
    -0.61
    ingle
    -0.59
    hood
    -0.58
    img
    -0.58
     Alfred
    -0.58
    POSITIVE LOGITS
     reasonable
    3.55
    reasonable
    2.85
     reasonably
    2.26
     sensible
    1.93
     unreasonable
    1.91
     plausible
    1.76
    asonable
    1.71
     sane
    1.71
     decent
    1.63
     feasible
    1.62
    Activations Density 0.012%

    No Known Activations