© 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. 8-RES-JB
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    conflicting concepts or opposing ideas in a text

    oai_token-act-pair · gpt-3.5-turbo

    themes related to conflict and contrasting desires for unity versus separation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jaguar
    -0.81
     enthusi
    -0.68
     Antar
    -0.67
     Nar
    -0.64
     XD
    -0.60
     Gow
    -0.59
    EMS
    -0.59
     Wik
    -0.58
    etc
    -0.58
     Kro
    -0.57
    POSITIVE LOGITS
    roying
    0.74
    èĥ
    0.73
     readiness
    0.65
    ield
    0.64
    isl
    0.63
     corresponding
    0.62
    actual
    0.60
     lifting
    0.60
     fulfilling
    0.59
    idy
    0.58
    Activations Density 0.724%

    No Known Activations