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. 3-RES-JB
    6. 22308
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or anatomical parts, specifically focusing on the term "hem" and "limb"

    oai_token-act-pair · gpt-3.5-turbo

    medical terms related to blood and bodily functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĺħâĺħ
    -0.81
    MJ
    -0.80
    HAEL
    -0.80
     AVG
    -0.77
    Builder
    -0.74
    Fresh
    -0.74
    ourke
    -0.72
     Agency
    -0.72
    ycle
    -0.72
    hire
    -0.71
    POSITIVE LOGITS
     hem
    1.24
    oglobin
    1.04
     separat
    0.95
     lobe
    0.92
    isphere
    0.92
    ically
    0.88
     tiss
    0.81
     circumference
    0.81
     ethn
    0.80
    iza
    0.80
    Activations Density 0.013%

    No Known Activations