© 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. 20213
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of the former US President Barack Obama

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Barack" and related contextual mentions

    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
     Debor
    -0.76
    senal
    -0.75
     livest
    -0.73
     eleph
    -0.73
     occas
    -0.71
     exha
    -0.68
     warr
    -0.64
     vend
    -0.64
    )].
    -0.63
    ĻĤ
    -0.63
    POSITIVE LOGITS
    enzie
    1.26
    intosh
    1.14
    luster
    0.96
    ademic
    0.96
    ery
    0.95
    nesses
    0.92
    NOW
    0.91
    acked
    0.91
    acks
    0.91
    ack
    0.89
    Activations Density 0.013%

    No Known Activations