© 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. 2-RES-JB
    11. 13525
    Prev
    Next
    INDEX
    Explanations

    words related to opportunities or opposing forces

    oai_token-act-pair · gpt-3.5-turbo

    words related to opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Newport
    -0.71
     Copenhagen
    -0.66
    ãģ®å®
    -0.65
     immersion
    -0.62
     Penal
    -0.62
    GO
    -0.61
     detector
    -0.59
     fine
    -0.59
     calcium
    -0.59
    GER
    -0.59
    POSITIVE LOGITS
    ortun
    1.50
    osite
    1.35
    onent
    1.34
    osition
    1.30
    onents
    1.13
    opp
    1.09
    odcast
    1.02
    olicy
    0.98
    osing
    0.97
    enf
    0.93
    Activations Density 0.004%

    No Known Activations