© 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. 2-RES-JB
    11. 6681
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names like "Korver" and "Koren" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals and references to the Koran

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.92
    enegger
    -0.83
    ãģ¦
    -0.82
     Democr
    -0.76
    ships
    -0.75
    ATURE
    -0.75
     Recover
    -0.71
    ATURES
    -0.70
    dress
    -0.70
    Accessory
    -0.70
    POSITIVE LOGITS
     Kor
    1.22
    anic
    1.10
     Klux
    1.03
    onite
    0.98
    anus
    0.88
    enei
    0.87
    anos
    0.83
    oton
    0.82
    oma
    0.82
    ikarp
    0.81
    Activations Density 0.007%

    No Known Activations