© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2630
    Prev
    Next
    INDEX
    Explanations

    questions and actions related to social interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    questions and interactions related to social behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    kefeller
    -0.80
     warehouses
    -0.75
     landfill
    -0.73
     Everest
    -0.73
    phalt
    -0.73
     Zurich
    -0.73
     PCB
    -0.73
    chwitz
    -0.72
     biotech
    -0.71
     Syndicate
    -0.70
    POSITIVE LOGITS
     gestures
    1.24
    verbal
    1.18
     pronouns
    1.16
     cues
    1.12
     greeting
    1.10
     pronoun
    1.10
     pauses
    1.09
     verbs
    1.09
     gesture
    1.07
     posture
    1.06
    Activations Density 0.612%

    No Known Activations