© 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. 2-RES-JB
    11. 19599
    Prev
    Next
    INDEX
    Explanations

    text related to genetics and health, particularly involving "GH" which often stands for Genomics and Health

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "GH" consistently across diverse contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.79
    nery
    -0.78
    uyomi
    -0.73
    andem
    -0.72
    lies
    -0.69
    sell
    -0.69
    Parent
    -0.66
    pron
    -0.65
    panic
    -0.65
    witz
    -0.64
    POSITIVE LOGITS
    GH
    1.11
    OST
    1.01
     GH
    0.94
    LLOW
    0.83
    OME
    0.82
    arrison
    0.80
     gh
    0.79
    APTER
    0.77
    urst
    0.74
    rowth
    0.73
    Activations Density 0.004%

    No Known Activations