© 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 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. 3-RES-JB
    11. 20258
    Prev
    Next
    INDEX
    Explanations

    organizations and abbreviations, particularly those related to finance and government interventions

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms related to specific programs and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.81
     Enrique
    -0.75
    ãĥĭ
    -0.73
    ãĥ´
    -0.72
     Devi
    -0.70
     Gh
    -0.70
    washer
    -0.70
    ãĤ¦ãĤ¹
    -0.70
     Chel
    -0.69
    eming
    -0.66
    POSITIVE LOGITS
    ARP
    1.21
    BALL
    0.97
    vernment
    0.95
    sonian
    0.93
    OPA
    0.86
    IUM
    0.85
    ACA
    0.85
    APP
    0.83
    olicy
    0.82
    ARA
    0.81
    Activations Density 0.015%

    No Known Activations