© 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. 10312
    Prev
    Next
    INDEX
    Explanations

    phrases related to keeping up-to-date on information

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to staying informed and up to date

    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
     clauses
    -0.58
     bankruptcy
    -0.58
     someday
    -0.57
     Extension
    -0.57
     minors
    -0.56
     il
    -0.56
     bonuses
    -0.55
     futures
    -0.54
     naming
    -0.54
     McDonnell
    -0.53
    POSITIVE LOGITS
    amped
    0.76
    rift
    0.74
    icket
    0.73
    ome
    0.72
    sight
    0.71
    oeuv
    0.71
    date
    0.69
    addle
    0.68
    leeve
    0.66
    ombat
    0.65
    Activations Density 0.190%

    No Known Activations