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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24121
    Prev
    Next
    INDEX
    Explanations

    terms related to politics, social issues, and government

    oai_token-act-pair · gpt-3.5-turbo

    terms related to political power and social inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUT
    -0.77
    Charges
    -0.75
    YN
    -0.67
     SUPPORT
    -0.66
     confir
    -0.64
    auder
    -0.64
    rompt
    -0.63
    everal
    -0.61
    request
    -0.61
    OFF
    -0.60
    POSITIVE LOGITS
     popul
    0.77
    ocracy
    0.76
     wars
    0.70
     thinkers
    0.70
     dystop
    0.69
     Capitalism
    0.69
     theorist
    0.69
     Communism
    0.69
     civilisation
    0.68
    ists
    0.67
    Activations Density 1.258%

    No Known Activations