© 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. 4-RES-JB
    11. 621
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Kyiv" (also known as Kiev), potentially linked to news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Ky"

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

    No Comments

    Negative Logits
    ional
    -0.93
    IBLE
    -0.81
    ãĥĩãĤ£
    -0.74
    heads
    -0.72
    bidden
    -0.71
    ions
    -0.70
    ACTED
    -0.69
     à¨
    -0.69
    ciation
    -0.68
    天
    -0.68
    POSITIVE LOGITS
    Ky
    1.02
    annis
    0.83
    ewitness
    0.82
     Ky
    0.82
    orea
    0.81
    kees
    0.80
    nect
    0.79
    jer
    0.78
    urnal
    0.77
    ©¶æ¥µ
    0.77
    Activations Density 0.007%

    No Known Activations