© 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. 9-RES-JB
    11. 11443
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or impact of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating large numbers or groups related to waves or floods of people, feelings, or events

    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
    vale
    -0.73
    ours
    -0.71
    acus
    -0.68
     differed
    -0.67
    few
    -0.66
    estamp
    -0.66
    heed
    -0.65
    ouf
    -0.65
    saf
    -0.65
    minus
    -0.65
    POSITIVE LOGITS
     negativity
    1.06
     criticism
    0.98
     publicity
    0.95
     discontent
    0.94
     arrivals
    0.87
     misinformation
    0.87
     submissions
    0.87
     complaints
    0.86
     indignation
    0.86
     lawsuits
    0.86
    Activations Density 0.156%

    No Known Activations