Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4377
    Prev
    Next
    INDEX
    Explanations

    medical terms related to specific types of cancers

    oai_token-act-pair · gpt-3.5-turbo

    references to health risks and diseases, particularly cancer

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isan
    -0.36
    ADVERTISEMENT
    -0.36
    tm
    -0.35
    uchin
    -0.35
    kell
    -0.34
    osaurs
    -0.34
     overseas
    -0.34
    azeera
    -0.34
     Opp
    -0.34
    ivated
    -0.33
    POSITIVE LOGITS
    etheless
    0.65
    awaru
    0.50
    agall
    0.48
     challeng
    0.47
     Citiz
    0.46
     rul
    0.45
    ingen
    0.44
     cryst
    0.44
     antioxid
    0.43
     tradem
    0.41
    Activations Density 1.990%

    No Known Activations