© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2308
    Prev
    Next
    INDEX
    Explanations

    instances where individuals are seeking or offering assistance

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases expressing the act of offering assistance or support

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    meier
    -0.76
    been
    -0.73
    levision
    -0.68
    bon
    -0.68
    ritical
    -0.66
    earable
    -0.66
    VERTISEMENT
    -0.65
    quickShipAvailable
    -0.62
    raining
    -0.62
    neum
    -0.60
    POSITIVE LOGITS
     alleviate
    1.08
     solve
    1.05
     facilitate
    1.03
     stabilize
    1.01
     organize
    1.00
     organise
    1.00
     educate
    0.99
     diagnose
    0.98
     mitigate
    0.97
     promote
    0.94
    Activations Density 0.068%

    No Known Activations