© 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. 0-RES-JB
    11. 4092
    Prev
    Next
    INDEX
    Explanations

    references to the name "Obama."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Obama

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     specialist
    -0.71
     suitable
    -0.68
     Channel
    -0.68
     variety
    -0.68
     mobile
    -0.67
     util
    -0.67
     sc
    -0.66
     superst
    -0.66
     Beh
    -0.65
     ar
    -0.65
    POSITIVE LOGITS
    Obama
    3.68
     Obama
    2.48
    Romney
    2.22
    Trump
    1.88
    Clinton
    1.79
     Barack
    1.76
    Bush
    1.74
    Putin
    1.74
    Hillary
    1.71
    Republicans
    1.70
    Activations Density 0.010%

    No Known Activations