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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19012
    Prev
    Next
    INDEX
    Explanations

    terms related to specific regions of the brain, such as the prefrontal cortex and parietal lobe

    oai_token-act-pair · gpt-3.5-turbo

    terms related 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cash
    -0.89
    Weather
    -0.71
    quickShipAvailable
    -0.70
     Nights
    -0.70
     Skies
    -0.69
    =-=-
    -0.68
    renheit
    -0.68
    Cash
    -0.67
    Legend
    -0.66
    Beer
    -0.66
    POSITIVE LOGITS
     gland
    1.13
     membranes
    1.02
     glands
    1.02
     anterior
    1.01
     protr
    0.97
     membrane
    0.96
     cortex
    0.96
     collagen
    0.93
     muscles
    0.92
     pores
    0.92
    Activations Density 0.159%

    No Known Activations