© 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. 2424
    Prev
    Next
    INDEX
    Explanations

    terms related to telecommunications, data plans, internet services, and government regulations

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

    terms related to telecommunications and the internet

    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
    ril
    -0.77
    raq
    -0.77
    Kate
    -0.76
    lain
    -0.73
    nee
    -0.72
    wine
    -0.70
     Frie
    -0.69
     Kate
    -0.69
    dyl
    -0.68
    agher
    -0.66
    POSITIVE LOGITS
     providers
    1.22
     provider
    1.15
     operators
    1.14
     operator
    1.12
     carriers
    1.09
     subscribers
    1.07
     monopoly
    1.04
     licences
    1.02
     tariffs
    1.00
     poles
    0.99
    Activations Density 0.149%

    No Known Activations