© 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. 2-RES-JB
    11. 12578
    Prev
    Next
    INDEX
    Explanations

    references to a "senator" within the context of various scenarios and discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to senators or political figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Disorder
    -0.78
    condition
    -0.76
    AMS
    -0.71
    gged
    -0.69
     Crew
    -0.69
     Condition
    -0.65
    ener
    -0.65
    vantage
    -0.62
    requisite
    -0.62
    ulia
    -0.62
    POSITIVE LOGITS
     senator
    1.01
    ially
    1.00
    ials
    0.86
    pai
    0.82
    uary
    0.81
    clinton
    0.80
    iors
    0.78
    ratulations
    0.77
     elector
    0.76
    nered
    0.74
    Activations Density 0.015%

    No Known Activations