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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 19451
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to medical conditions and diseases

    oai_token-act-pair · gpt-3.5-turbo
    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
    soDeliveryDate
    -1.03
     desks
    -0.83
     rooft
    -0.80
    atron
    -0.77
     Bezos
    -0.75
     booths
    -0.75
     booth
    -0.74
    Tokens
    -0.73
    awei
    -0.72
    externalActionCode
    -0.71
    POSITIVE LOGITS
     Symptoms
    1.47
     symptoms
    1.34
     disease
    1.25
     syndrome
    1.22
     neurological
    1.22
     inflammation
    1.20
     illnesses
    1.20
     diseases
    1.19
    ptoms
    1.18
     hereditary
    1.16
    Activations Density 0.410%

    No Known Activations