© 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. 12995
    Prev
    Next
    INDEX
    Explanations

    references to historical events or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political power dynamics and influences within the U.S

    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
     Operator
    -0.75
    :(
    -0.74
    !!!!!!!!
    -0.68
     Engineers
    -0.68
     UNIVERS
    -0.67
     Explan
    -0.65
    ISSION
    -0.65
    terday
    -0.64
     :=
    -0.64
    eria
    -0.64
    POSITIVE LOGITS
     staunch
    0.97
     hostile
    0.84
     unfavorable
    0.84
     fract
    0.82
     strained
    0.81
     unpopular
    0.80
     notoriously
    0.79
     hostility
    0.79
     fiercely
    0.78
     disdain
    0.78
    Activations Density 0.526%

    No Known Activations