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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 10090
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions and diseases, specifically focusing on AIDS and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to AIDS and related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbers
    -0.86
    aries
    -0.82
    eneg
    -0.81
    idable
    -0.81
    umbing
    -0.81
    umber
    -0.80
    less
    -0.79
    ivating
    -0.79
    ivas
    -0.79
    iple
    -0.78
    POSITIVE LOGITS
     Relief
    0.74
     Revelations
    0.70
     Appeal
    0.69
     Capitalism
    0.67
     cz
    0.67
    eering
    0.66
     Leone
    0.66
     Bomber
    0.65
     Healthcare
    0.64
     Worker
    0.64
    Activations Density 0.022%

    No Known Activations