© 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. 1-RES-JB
    11. 11173
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals, particularly Hosni Mubarak and Sik

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scotia
    -0.75
     Samoa
    -0.72
    shapeshifter
    -0.70
     Volks
    -0.69
     Geographic
    -0.68
     Hurricanes
    -0.66
     Commonwealth
    -0.65
     Wonderland
    -0.63
    âĢ¢âĢ¢
    -0.63
     Drunk
    -0.63
    POSITIVE LOGITS
     Hos
    1.13
    sein
    1.09
    kinson
    1.03
    oslav
    1.00
    iery
    0.98
    kins
    0.95
    nian
    0.91
    iak
    0.87
    mers
    0.87
    eni
    0.87
    Activations Density 0.004%

    No Known Activations