© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11690
    Prev
    Next
    INDEX
    Explanations

    the name "Rod" followed by a variety of letters that may indicate different individuals or variations of the name

    oai_token-act-pair · gpt-3.5-turbo

    the name "Rod" and its variations or derivatives

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.62
    places
    -0.58
     procedure
    -0.57
     fries
    -0.56
    izations
    -0.56
     regulator
    -0.56
    OPS
    -0.56
     Columb
    -0.56
     expenditure
    -0.55
     pack
    -0.55
    POSITIVE LOGITS
    erick
    1.33
    rig
    1.15
    gers
    1.09
    olf
    1.04
    ger
    0.99
    eway
    0.96
    rique
    0.95
    ricks
    0.94
    ents
    0.91
    rick
    0.91
    Activations Density 0.041%

    No Known Activations