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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 24385
    Prev
    Next
    INDEX
    Explanations

    specific types of receptors, likely related to medical or scientific contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological receptors, particularly in the context of cannabinoid receptors

    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
     Prosper
    -0.77
    yre
    -0.74
    Beat
    -0.73
     Chatt
    -0.71
    swick
    -0.70
    estamp
    -0.69
    cas
    -0.69
     Jobs
    -0.68
     Appalachian
    -0.68
    hur
    -0.67
    POSITIVE LOGITS
     antagonist
    1.05
     antagonists
    1.05
     receptor
    1.03
     receptors
    1.01
     agon
    1.00
     lig
    0.83
     signaling
    0.82
     antibody
    0.80
     blocker
    0.80
     glands
    0.80
    Activations Density 0.010%

    No Known Activations