© 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. 9-RES-JB
    11. 23956
    Prev
    Next
    INDEX
    Explanations

    positive characteristics or qualities related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    descriptive adjectives and phrases that convey admiration and positive attributes about individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    piracy
    -0.78
    ãĥ¯ãĥ³
    -0.76
    ilater
    -0.75
    idential
    -0.75
    scroll
    -0.74
    FAQ
    -0.67
    afety
    -0.67
     legality
    -0.66
     multiplication
    -0.66
    iatus
    -0.65
    POSITIVE LOGITS
     qualities
    1.13
     traits
    0.97
     temperament
    0.89
     conducive
    0.84
     charisma
    0.83
     lacking
    0.82
     adject
    0.80
     characterize
    0.79
     contrasted
    0.78
     suited
    0.75
    Activations Density 0.789%

    No Known Activations