© 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. 1770
    Prev
    Next
    INDEX
    Explanations

    phrases related to the medical condition hypothyroidism

    oai_token-act-pair · gpt-3.5-turbo

    words related to excitement or anticipation

    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
     Tanz
    -0.83
    jar
    -0.82
    bridge
    -0.80
     Bei
    -0.77
    fell
    -0.73
     FML
    -0.73
    acker
    -0.72
    wagen
    -0.70
     Settlement
    -0.69
     Forestry
    -0.69
    POSITIVE LOGITS
     hyp
    3.85
    hyp
    2.59
     Hyp
    2.53
    Hyp
    2.38
     hypnot
    1.70
     HY
    1.47
     hype
    1.41
     hyper
    1.38
    Hyper
    1.37
     Hyper
    1.23
    Activations Density 0.023%

    No Known Activations