© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11740
    Prev
    Next
    INDEX
    Explanations

    terms related to power dynamics and dominance in social interactions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to dominance and authority in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iago
    -0.77
     busted
    -0.76
     Sov
    -0.71
    çīĪ
    -0.71
     goddamn
    -0.67
     Canaver
    -0.66
    ovember
    -0.63
     godd
    -0.63
     sued
    -0.63
    phalt
    -0.62
    POSITIVE LOGITS
     behaviors
    1.33
     behaviours
    1.22
    fulness
    1.02
    behavior
    1.01
     demeanor
    0.99
     interpersonal
    0.96
     feelings
    0.96
     emotionally
    0.95
     cues
    0.95
     behavior
    0.95
    Activations Density 0.442%

    No Known Activations