© 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. 22591
    Prev
    Next
    INDEX
    Explanations

    medical treatments related to cancer, particularly chemotherapy, and medical care settings like hospices

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemotherapy and medical treatment related to cancer

    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
    assic
    -0.96
    agall
    -0.78
    ional
    -0.77
    oral
    -0.77
    Ocean
    -0.73
    aired
    -0.71
    urb
    -0.71
    Balance
    -0.71
    ifax
    -0.71
    Republic
    -0.70
    POSITIVE LOGITS
     chemotherapy
    1.02
     hosp
    0.78
     treatments
    0.76
    zed
    0.75
     leukemia
    0.73
     Surgery
    0.70
     treatment
    0.70
    \<
    0.68
     decomp
    0.68
     cancer
    0.68
    Activations Density 0.017%

    No Known Activations