© 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. 2435
    Prev
    Next
    INDEX
    Explanations

    situations or places where someone finds something or somewhere, often related to humanitarian or community efforts

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

    phrases emphasizing opportunities, potential, and new beginnings

    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
    naires
    -0.74
    otypes
    -0.72
    ÙĨ
    -0.71
    sbm
    -0.70
    idium
    -0.70
    oids
    -0.69
    ICO
    -0.68
     Expect
    -0.65
    imar
    -0.65
    upt
    -0.65
    POSITIVE LOGITS
     loophole
    1.25
     way
    1.15
     footing
    1.13
     groove
    1.12
     niche
    1.12
     solution
    1.09
     kindred
    1.07
     foothold
    1.07
     scapego
    1.06
     receptive
    1.05
    Activations Density 0.180%

    No Known Activations