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

    Neuronpedia

    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. 1-RES-JB
    11. 12892
    Prev
    Next
    INDEX
    Explanations

    words related to positions of authority or leadership

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals holding the title of vice president

    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
     smugglers
    -0.75
     hitch
    -0.74
    ramid
    -0.67
     handc
    -0.66
     classify
    -0.66
     IMAGES
    -0.65
    FER
    -0.64
    anche
    -0.64
    nikov
    -0.63
    âĨij
    -0.63
    POSITIVE LOGITS
    stown
    0.95
    ially
    0.95
    ial
    0.94
    ials
    0.92
    iors
    0.91
    president
    0.91
    bernatorial
    0.87
    itatively
    0.86
    furt
    0.85
    iate
    0.83
    Activations Density 0.006%

    No Known Activations