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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 16768
    Prev
    Next
    INDEX
    Explanations

    organizations or programs related to funding and philanthropy

    oai_token-act-pair · gpt-3.5-turbo

    references to various funds and funding organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èª
    -0.75
     apparel
    -0.73
    obyl
    -0.64
    âĹ¼
    -0.63
     hypers
    -0.62
     courthouse
    -0.62
     garment
    -0.62
     sher
    -0.61
    MT
    -0.61
    Sil
    -0.61
    POSITIVE LOGITS
     Fund
    1.30
    ament
    1.21
    raising
    1.05
    amental
    1.04
    fund
    1.03
    Fund
    1.02
     Funds
    0.99
     Advis
    0.96
    aments
    0.88
    folios
    0.86
    Activations Density 0.006%

    No Known Activations