© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 8242
    Prev
    Next
    INDEX
    Explanations

    terms related to neurotransmitters and drugs

    oai_token-act-pair · gpt-3.5-turbo

    chemical compounds related to drugs and neurotransmitters

    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
    Ship
    -0.80
     IEEE
    -0.80
     Nieto
    -0.77
    Earth
    -0.77
    earth
    -0.76
     Petty
    -0.75
     Celest
    -0.71
    Corn
    -0.70
     Qian
    -0.70
     Piece
    -0.69
    POSITIVE LOGITS
    phrine
    1.14
    ergic
    1.09
    amphetamine
    1.08
     neurotrans
    1.07
     supplementation
    1.06
    amines
    1.06
     steroids
    1.00
     serotonin
    0.97
     sulf
    0.97
     dopamine
    0.96
    Activations Density 0.055%

    No Known Activations