© 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. 10-RES-JB
    11. 16026
    Prev
    Next
    INDEX
    Explanations

    mentions of organizations or groups related to political or social causes

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "freedom."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    manship
    -0.77
    urally
    -0.76
    enance
    -0.74
    isations
    -0.67
    ictions
    -0.65
     incompet
    -0.65
    agers
    -0.64
    hetically
    -0.64
    matically
    -0.63
     alike
    -0.63
    POSITIVE LOGITS
    Works
    0.97
     Alley
    0.90
     Partners
    0.90
     Clinic
    0.89
     Matters
    0.89
     Lobby
    0.88
     Corps
    0.88
     Meter
    0.87
     Fighters
    0.85
    Fest
    0.85
    Activations Density 0.107%

    No Known Activations