© 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. 10-RES-JB
    6. 7151
    Prev
    Next
    INDEX
    Explanations

    phrases related to political or social conflict

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and political oppression

    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
    ©¶æ¥µ
    -0.91
     Skip
    -0.89
     Laser
    -0.87
     Swap
    -0.81
     Pinball
    -0.76
     Zup
    -0.75
    Legend
    -0.74
    Scroll
    -0.72
     Merlin
    -0.71
     Yamaha
    -0.71
    POSITIVE LOGITS
     societal
    1.28
     nonviolent
    1.26
     democracies
    1.25
     insurg
    1.19
     interpersonal
    1.19
     societies
    1.18
     crises
    1.16
     repressive
    1.16
     authoritarian
    1.15
     democratic
    1.15
    Activations Density 0.898%

    No Known Activations