© 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. 6310
    Prev
    Next
    INDEX
    Explanations

    social media interactions related to account blocking and unblocking

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social media interactions and connections

    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
     toughness
    -0.74
     crest
    -0.73
     preparation
    -0.71
     wreck
    -0.69
     disinteg
    -0.69
     dressing
    -0.68
     fabrication
    -0.68
     foremost
    -0.68
     quarters
    -0.67
     concoct
    -0.67
    POSITIVE LOGITS
     Users
    1.07
    Offline
    1.04
    edIn
    1.03
     Detected
    0.99
     Us
    0.98
     Offline
    0.96
     Accounts
    0.96
     Ads
    0.94
    ables
    0.93
     User
    0.90
    Activations Density 0.075%

    No Known Activations