© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9484
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mubarak" in a political context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Hosni Mubarak

    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
    amins
    -0.81
    RAFT
    -0.78
     Scotch
    -0.77
    ivity
    -0.74
    PASS
    -0.73
    WARD
    -0.72
     Nationwide
    -0.71
    itialized
    -0.71
    Lex
    -0.68
    hips
    -0.68
    POSITIVE LOGITS
     Mubarak
    1.26
     Morsi
    1.06
     Gaddafi
    0.81
    ovich
    0.80
     Jinping
    0.79
    abad
    0.77
    ascus
    0.75
     Abedin
    0.75
    ilon
    0.73
     Abbas
    0.73
    Activations Density 0.010%

    No Known Activations