© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12324
    Prev
    Next
    INDEX
    Explanations

    terms related to populations or groups, especially in the context of demographics or statistics

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups and their characteristics

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

    No Comments

    Negative Logits
    ipedia
    -0.78
    pit
    -0.76
    rah
    -0.76
    hemy
    -0.76
    amina
    -0.75
    lain
    -0.75
    shire
    -0.75
    ouston
    -0.74
    paio
    -0.73
    ñ
    -0.71
    POSITIVE LOGITS
     demographic
    1.01
     demographics
    1.00
     profiles
    0.84
     profile
    0.77
     pressures
    0.76
     variables
    0.74
     breakdown
    0.74
     characteristics
    0.74
     warfare
    0.73
     backgrounds
    0.72
    Activations Density 0.012%

    No Known Activations