© 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. 3-RES-JB
    11. 5714
    Prev
    Next
    INDEX
    Explanations

    mentions of the city "Minsk" and related agreements or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the Minsk agreements and military troop movements

    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
    nces
    -0.82
    hemy
    -0.81
    essor
    -0.80
    aurus
    -0.78
    sembly
    -0.73
    itiveness
    -0.73
    undo
    -0.72
    markets
    -0.72
    emis
    -0.71
    chnology
    -0.71
    POSITIVE LOGITS
     stride
    0.88
     Archdemon
    0.79
    insk
    0.78
     Weir
    0.71
    ãĥĥãĥī
    0.69
     Gibraltar
    0.68
    è¦ļéĨĴ
    0.66
    animous
    0.65
     AFB
    0.65
     Declaration
    0.65
    Activations Density 0.027%

    No Known Activations