© 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. 8-RES-JB
    11. 12815
    Prev
    Next
    INDEX
    Explanations

    instances where a pronoun "they" is associated with a verb or action

    oai_token-act-pair · gpt-3.5-turbo

    references to people or groups of people, particularly in a context suggesting vulnerability or need

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eleven
    -0.84
    CCC
    -0.67
     Owl
    -0.67
     Glob
    -0.65
     Sequ
    -0.63
     Kinn
    -0.63
    Rating
    -0.63
     Globe
    -0.63
     Twelve
    -0.62
     Flan
    -0.62
    POSITIVE LOGITS
    're
    1.56
    've
    1.25
     themselves
    1.20
    'll
    1.17
    selves
    1.13
    'd
    1.11
     are
    1.05
     selves
    1.03
     perceive
    0.98
     were
    0.97
    Activations Density 0.245%

    No Known Activations