© 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. 14300
    Prev
    Next
    INDEX
    Explanations

    phrases related to the political figure "Robert Mugabe"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the names Mugabe and Sudeten

    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
    Ħ¢
    -0.82
     Stockholm
    -0.73
    ¯¯¯¯
    -0.72
    orney
    -0.72
    ¯¯
    -0.71
    etheless
    -0.70
     diarr
    -0.68
    senal
    -0.66
     rift
    -0.66
     aeros
    -0.64
    POSITIVE LOGITS
    olini
    0.95
     Muss
    0.80
    imoto
    0.80
     Hussein
    0.78
    rats
    0.77
    insk
    0.76
    jug
    0.74
    ler
    0.73
    enes
    0.73
    trap
    0.73
    Activations Density 0.012%

    No Known Activations