© 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. 1-RES-JB
    11. 21279
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Boris" and context related to him

    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
    FOX
    -0.71
    ocrine
    -0.69
    ORE
    -0.67
    ULT
    -0.67
    ursed
    -0.66
    mary
    -0.65
    prise
    -0.65
    ART
    -0.64
    TPS
    -0.64
    WORK
    -0.64
    POSITIVE LOGITS
     Boris
    1.39
     Yel
    1.06
    achev
    0.99
     Dia
    0.87
    adiq
    0.86
    ovich
    0.85
     Dmitry
    0.81
     Bere
    0.76
     Zac
    0.75
    sov
    0.75
    Activations Density 0.002%

    No Known Activations