© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 20502
    Prev
    Next
    INDEX
    Explanations

    names of states in the United States of America

    oai_token-act-pair · gpt-3.5-turbo

    identifiers of states and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oyal
    -0.68
     adapt
    -0.68
    atos
    -0.68
    isations
    -0.67
     adaptations
    -0.67
    ongyang
    -0.65
     behaviours
    -0.65
     favourites
    -0.64
    ariat
    -0.64
     rapport
    -0.64
    POSITIVE LOGITS
    ornia
    0.78
     ILCS
    0.73
    Ĥİ
    0.70
     Transportation
    0.69
     Boone
    0.68
     Mellon
    0.68
     Toll
    0.67
    edu
    0.67
     Clerk
    0.66
     Stout
    0.66
    Activations Density 0.982%

    No Known Activations