© 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. 2284
    Prev
    Next
    INDEX
    Explanations

    language related to social or political issues and statements condemning violence or unethical behavior

    oai_token-act-pair · gpt-3.5-turbo

    expressions of condemnation or denunciation regarding violence and human rights abuses

    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
    ortality
    -0.82
    ©¶æ¥µ
    -0.79
     retirees
    -0.76
    luck
    -0.74
    igree
    -0.73
     Quartz
    -0.71
    soDeliveryDate
    -0.70
     Jennings
    -0.69
     Gins
    -0.69
    noticed
    -0.69
    POSITIVE LOGITS
     hateful
    1.35
     intolerance
    1.29
     bigotry
    1.27
     discriminatory
    1.27
     unlawful
    1.25
     bullying
    1.23
     hatred
    1.19
     slander
    1.18
     malicious
    1.18
     misuse
    1.17
    Activations Density 0.503%

    No Known Activations