© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    names of specific political figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly politicians

    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
    ripp
    -0.92
    fman
    -0.92
    BOOK
    -0.83
    chrom
    -0.82
    hered
    -0.79
    Seattle
    -0.78
    naire
    -0.77
    plex
    -0.77
    earing
    -0.77
    bodied
    -0.76
    POSITIVE LOGITS
     Mahmoud
    1.22
     Abbas
    1.08
     Ahmad
    0.90
     Mahm
    0.87
    ollah
    0.86
     Gh
    0.86
     Mubarak
    0.84
     Ahmed
    0.80
     Meh
    0.79
     Abdel
    0.79
    Activations Density 0.011%

    No Known Activations