© 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. 4933
    Prev
    Next
    INDEX
    Explanations

    information about political events, organizations, and activities

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

    the presence of the letter "A" at the beginning of sentences or phrases

    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
    oids
    -0.76
     engagements
    -0.71
     NPCs
    -0.70
     interests
    -0.68
     outlets
    -0.67
     enemies
    -0.67
     intervals
    -0.67
     whatsoever
    -0.66
     appointments
    -0.65
     formats
    -0.65
    POSITIVE LOGITS
    UST
    1.11
    uckland
    1.08
    UG
    1.00
    erial
    0.92
    ircraft
    0.90
    mber
    0.89
    usterity
    0.88
    UTH
    0.87
    ctors
    0.86
    gency
    0.86
    Activations Density 0.106%

    No Known Activations