© 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. 0-RES-JB
    11. 20099
    Prev
    Next
    INDEX
    Explanations

    mentions of populations and demographic groups

    oai_token-act-pair · gpt-3.5-turbo

    references to demographics or groups of people

    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
    orthy
    -0.64
     Canon
    -0.63
    rant
    -0.62
     Cancel
    -0.60
     Comedy
    -0.58
    Accessory
    -0.58
     farewell
    -0.58
     Susp
    -0.58
     Mir
    -0.57
    shop
    -0.57
    POSITIVE LOGITS
     populations
    3.62
     population
    2.35
    population
    2.08
    Population
    1.82
     Population
    1.72
     communities
    1.61
     demographics
    1.55
     genomes
    1.54
     economies
    1.52
     societies
    1.47
    Activations Density 0.012%

    No Known Activations