© 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. 8-RES-JB
    11. 7011
    Prev
    Next
    INDEX
    Explanations

    specific regions of the brain, like the prefrontal cortex and dorsomedial prefrontal cortex

    oai_token-act-pair · gpt-3.5-turbo

    references to brain regions and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rave
    -0.78
    soDeliveryDate
    -0.78
    glers
    -0.76
     Breed
    -0.74
     Armageddon
    -0.73
     Wasteland
    -0.68
     Fraud
    -0.68
    Rated
    -0.67
    Jet
    -0.67
     scares
    -0.67
    POSITIVE LOGITS
     neurons
    1.31
     cortex
    1.25
     cortical
    1.22
     neuronal
    1.16
     dopamine
    1.16
     neuron
    1.14
    insula
    1.13
     serotonin
    1.11
     prefrontal
    1.08
     hippocampus
    1.07
    Activations Density 0.133%

    No Known Activations