© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and industry developments, specifically focusing on projects and agreements

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

    terms related to energy technologies and various vehicle types, particularly in the context of electric and hybrid vehicles

    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
    76561
    -1.17
    ovies
    -0.89
    cffffcc
    -0.78
    NetMessage
    -0.77
    umbs
    -0.75
    Ļ½
    -0.74
    posts
    -0.73
    quickShipAvailable
    -0.73
     Rocks
    -0.72
    @#&
    -0.70
    POSITIVE LOGITS
     prototype
    1.22
     demonstr
    1.05
     prototypes
    1.04
     system
    0.99
     capable
    0.96
     platform
    0.95
     concept
    0.92
     variant
    0.92
     solution
    0.92
    liner
    0.90
    Activations Density 0.312%

    No Known Activations