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. 10-RES-JB
    6. 23743
    Prev
    Next
    INDEX
    Explanations

    words related to biological compounds and mechanisms within the human body

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to biochemical processes and their components in the body

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.79
    illion
    -0.79
    intend
    -0.79
    soDeliveryDate
    -0.78
    udget
    -0.76
    join
    -0.76
    lege
    -0.75
    edd
    -0.75
    uously
    -0.74
    ult
    -0.74
    POSITIVE LOGITS
     digestive
    1.29
     bloodstream
    1.29
     neurotrans
    1.27
     brain
    1.26
     enzyme
    1.26
     organism
    1.25
     mammalian
    1.24
     lungs
    1.24
     fetus
    1.21
     brains
    1.18
    Activations Density 0.223%

    No Known Activations