© 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. 2529
    Prev
    Next
    INDEX
    Explanations

    verbs followed by pronouns or directions

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

    active verbs indicating movement or action

    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
    SPONSORED
    -0.42
     Bureau
    -0.39
     ÂŃ
    -0.39
     principals
    -0.39
     likelihood
    -0.38
     contributing
    -0.37
     concession
    -0.37
     proposed
    -0.37
     enlisted
    -0.37
     rationale
    -0.37
    POSITIVE LOGITS
     Slowly
    0.63
     DOWN
    0.63
     ashore
    0.62
    !:
    0.62
     INTO
    0.61
     sideways
    0.59
     Away
    0.59
     awa
    0.58
    !".
    0.58
    !",
    0.57
    Activations Density 0.538%

    No Known Activations