© 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. 20596
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or political issues

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and resilience in challenging situations

    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
    Desktop
    -0.61
    uum
    -0.61
    Cor
    -0.61
    illes
    -0.60
    ĪĴ
    -0.59
    endars
    -0.58
     Howe
    -0.58
     Greenwood
    -0.57
    ACC
    -0.57
    burgh
    -0.57
    POSITIVE LOGITS
    inois
    0.79
     iss
    0.73
    ppo
    0.71
    uca
    0.69
    Reviewer
    0.68
    olean
    0.61
     Quote
    0.61
     pokemon
    0.61
     Posted
    0.60
     Logged
    0.60
    Activations Density 0.327%

    No Known Activations