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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13501
    Prev
    Next
    INDEX
    Explanations

    phrases with hyphenated words, especially those related to technical or specialized fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific and academic concepts

    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
    utics
    -0.72
    ;;
    -0.67
     Wells
    -0.66
    ;;;;;;;;
    -0.65
     ..........
    -0.65
    ilaterally
    -0.63
     Including
    -0.62
     Disorder
    -0.61
     Month
    -0.61
    onis
    -0.60
    POSITIVE LOGITS
    liest
    0.99
     aspect
    0.97
     nature
    0.95
    iest
    0.93
     portion
    0.92
     component
    0.91
     element
    0.90
     version
    0.89
     hypothesis
    0.88
     keyword
    0.88
    Activations Density 0.616%

    No Known Activations