© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 6396
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions and treatments

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cancer and related terms

    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
    stanbul
    -0.83
    BOOK
    -0.82
    worldly
    -0.73
    rish
    -0.70
    theless
    -0.70
    Snap
    -0.69
    é¾įåĸļ士
    -0.68
    ership
    -0.68
     Polk
    -0.68
    Atl
    -0.66
    POSITIVE LOGITS
    ous
    1.27
     cancer
    1.09
     metast
    1.04
     diagnosis
    1.03
     chemotherapy
    1.03
     tumors
    0.99
    cancer
    0.98
     screenings
    0.96
     diagnoses
    0.96
     survivor
    0.95
    Activations Density 0.040%

    No Known Activations