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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11223
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and entities

    oai_token-act-pair · gpt-3.5-turbo

    formal references to educational institutions and their governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Afee
    -0.76
    76561
    -0.73
     Razer
    -0.73
     docker
    -0.73
    Coin
    -0.72
    coin
    -0.70
     liqu
    -0.66
     Wraith
    -0.65
    BTC
    -0.64
    fu
    -0.64
    POSITIVE LOGITS
     teachers
    2.16
     classrooms
    2.12
     classroom
    2.11
     teacher
    2.05
    School
    2.02
     school
    2.02
     educators
    1.98
     schools
    1.97
     curriculum
    1.96
     Teachers
    1.95
    Activations Density 1.224%

    No Known Activations