© 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. 3-RES-JB
    11. 2988
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to Nordic countries and associated terms

    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
    inventoryQuantity
    -1.02
    =-=-=-=-
    -0.76
    ++++++++++++++++
    -0.74
    QUI
    -0.70
    ģĸ
    -0.69
    Ĥİ
    -0.66
    ODUCT
    -0.65
    veyard
    -0.65
    Package
    -0.65
    ================================================================
    -0.63
    POSITIVE LOGITS
     Nord
    1.06
    strom
    0.99
    lund
    0.88
    sson
    0.87
    isk
    0.86
    quist
    0.85
    eway
    0.84
    ril
    0.84
    VPN
    0.84
    isson
    0.83
    Activations Density 0.008%

    No Known Activations