© 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. 10-RES-JB
    11. 3302
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the potential for making a positive impact through various actions, such as speaking up, voting, offering support, and sharing feedback

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to influence or making a difference

    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
     Purg
    -0.87
     Brun
    -0.75
    hid
    -0.71
    BSD
    -0.69
    olitan
    -0.65
     Vul
    -0.65
    ylum
    -0.64
     Relax
    -0.63
    Abstract
    -0.63
     Gleaming
    -0.60
    POSITIVE LOGITS
     impact
    1.37
     influence
    1.33
    impact
    1.29
     influencing
    1.29
     Influence
    1.24
     impacting
    1.18
     mattered
    1.09
     invaluable
    1.06
     affect
    1.06
     Impact
    1.06
    Activations Density 0.568%

    No Known Activations