© 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. 3-RES-JB
    11. 9221
    Prev
    Next
    INDEX
    Explanations

    terms related to biological signaling pathways, proteins, and molecular regulatory mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biochemical signaling molecules and processes

    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
    soDeliveryDate
    -0.81
    Hour
    -0.80
    Weather
    -0.79
    é¾
    -0.79
    BuyableInstoreAndOnline
    -0.77
    fell
    -0.77
    Civil
    -0.73
    Vict
    -0.71
    Dash
    -0.71
    DEM
    -0.70
    POSITIVE LOGITS
     receptor
    1.25
     enzymes
    1.23
     proteins
    1.20
     neurotrans
    1.19
     enzyme
    1.19
     signaling
    1.19
     receptors
    1.18
     inhibit
    1.15
     protein
    1.15
     inhibitor
    1.12
    Activations Density 0.549%

    No Known Activations