© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2981
    Prev
    Next
    INDEX
    Explanations

    information about employment trends in various sectors, such as retail, healthcare, and coal industry

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    economic indicators and trends related to job markets and trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    iquette
    -0.68
     NEVER
    -0.65
    ĨĴ
    -0.65
     Constitutional
    -0.64
     ACLU
    -0.63
     recite
    -0.61
    NRS
    -0.61
     Genocide
    -0.61
     validity
    -0.61
     impartial
    -0.61
    POSITIVE LOGITS
     amid
    0.91
     slumped
    0.88
     slowing
    0.86
     lately
    0.86
     shrinking
    0.83
     slowed
    0.82
     spurred
    0.81
    ustomed
    0.78
     boosted
    0.77
     exacerbated
    0.77
    Activations Density 0.497%

    No Known Activations