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. 4-RES-JB
    6. 5310
    Prev
    Next
    INDEX
    Explanations

    a medical condition related to low blood sugar levels

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hypoglycemia and notable individuals associated with it

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

    No Comments

    Negative Logits
    nered
    -0.90
     Parenthood
    -0.77
    een
    -0.71
     Gaul
    -0.71
     Kut
    -0.70
     Unlimited
    -0.66
     Purg
    -0.65
    Merit
    -0.64
     Blackburn
    -0.64
     TAMADRA
    -0.63
    POSITIVE LOGITS
    pha
    1.03
    andise
    0.90
    terday
    0.83
    cemic
    0.83
    uate
    0.81
    hematic
    0.81
    idered
    0.80
    tch
    0.80
    oric
    0.80
    mph
    0.80
    Activations Density 0.038%

    No Known Activations