© 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. 9-RES-JB
    11. 10268
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by the verb 'to have.'

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to personal and group identities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Majority
    -0.70
     Sapp
    -0.68
     Dunk
    -0.66
     Globe
    -0.65
     Agg
    -0.65
    luster
    -0.62
     Lobby
    -0.61
     Hau
    -0.61
     Bundes
    -0.60
     Gutenberg
    -0.59
    POSITIVE LOGITS
    athed
    1.06
    've
    1.00
    RL
    0.99
    uristic
    0.97
     hadn
    0.97
     deems
    0.95
    'd
    0.94
     deem
    0.92
     couldn
    0.91
    arers
    0.86
    Activations Density 0.144%

    No Known Activations