© 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. 8-RES-JB
    11. 6300
    Prev
    Next
    INDEX
    Explanations

    mentions of medical professionals such as physicians or specialists

    oai_token-act-pair · gpt-3.5-turbo

    words ending with the suffix "ist"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    culosis
    -0.72
    Reviewer
    -0.72
    accompanied
    -0.70
    ilings
    -0.69
    Dub
    -0.68
    ilater
    -0.67
    gee
    -0.67
    BOX
    -0.65
     poorer
    -0.62
    perty
    -0.62
    POSITIVE LOGITS
    ophe
    1.14
    ocrat
    1.04
    ribution
    1.01
    opher
    0.99
    orical
    0.99
    rict
    0.98
    otle
    0.97
    ribut
    0.92
    ocene
    0.91
    ricting
    0.89
    Activations Density 0.060%

    No Known Activations