© 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. 11-RES-JB
    11. 12933
    Prev
    Next
    INDEX
    Explanations

    terms related to theoretical concepts and ideologies

    oai_token-act-pair · gpt-3.5-turbo

    clauses that introduce explanations or definitions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Tickets
    -0.74
    done
    -0.71
    itone
    -0.71
    Done
    -0.66
    Interstitial
    -0.66
    paying
    -0.66
    VER
    -0.65
     Auditor
    -0.64
     earthqu
    -0.62
    catching
    -0.62
    POSITIVE LOGITS
     emphasizes
    1.58
     revolves
    1.53
     involves
    1.45
     relies
    1.40
     incorporates
    1.39
     focuses
    1.37
     assumes
    1.35
     encompasses
    1.31
     embraces
    1.30
     seeks
    1.30
    Activations Density 0.269%

    No Known Activations