© 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. 14199
    Prev
    Next
    INDEX
    Explanations

    names of people, likely focusing on surnames

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to individuals and entities with the prefix "Sch."

    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
     GOODMAN
    -0.77
     Dying
    -0.69
     disapp
    -0.68
     underwater
    -0.63
     trainers
    -0.60
     DRAG
    -0.59
     slee
    -0.58
     goodbye
    -0.57
     ay
    -0.57
     deprivation
    -0.55
    POSITIVE LOGITS
    itzer
    1.04
    artz
    1.00
    uble
    0.94
    acher
    0.92
    enberg
    0.92
    interstitial
    0.92
    inger
    0.91
    efer
    0.87
    owsky
    0.86
    lich
    0.86
    Activations Density 0.057%

    No Known Activations