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. 11-RES-JB
    6. 7420
    Prev
    Next
    INDEX
    Explanations

    terms related to drugs and their effects on the brain

    oai_token-act-pair · gpt-3.5-turbo

    references to neurotransmitters and their effects on the body

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.80
    wered
    -0.78
     Crawford
    -0.78
    igans
    -0.76
    rust
    -0.75
    BuyableInstoreAndOnline
    -0.74
     Garn
    -0.73
     Flint
    -0.72
    iece
    -0.72
    silver
    -0.71
    POSITIVE LOGITS
     dopamine
    1.87
     neurotrans
    1.75
     serotonin
    1.51
     GABA
    1.48
     receptors
    1.45
     opio
    1.35
     receptor
    1.35
     stimul
    1.34
     dop
    1.32
    otonin
    1.30
    Activations Density 0.217%

    No Known Activations