© 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. 5105
    Prev
    Next
    INDEX
    Explanations

    words related to clarity and decisive conclusions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    assertions of clarity or transparency about situations and events

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    gins
    -0.69
    inse
    -0.62
    inia
    -0.61
    inqu
    -0.59
     livest
    -0.58
    pes
    -0.56
    rette
    -0.55
    Limited
    -0.54
    optional
    -0.54
    UID
    -0.54
    POSITIVE LOGITS
     why
    1.11
     that
    0.93
     how
    0.88
     WHY
    0.85
    why
    0.83
     what
    0.82
     to
    0.81
     from
    0.79
     enough
    0.78
     whether
    0.77
    Activations Density 0.085%

    No Known Activations