© 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 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. 20128
    Prev
    Next
    INDEX
    Explanations

    phrases related to collections or items for sale

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to content that offers information or resources

    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
    soType
    -0.87
    osis
    -0.85
    sis
    -0.74
    Prosecut
    -0.68
    externalActionCode
    -0.68
    人
    -0.67
    TPP
    -0.67
    Merit
    -0.67
    necess
    -0.66
    arent
    -0.64
    POSITIVE LOGITS
     curated
    1.10
     dozens
    1.08
     excerpts
    1.05
     listings
    1.03
     assorted
    0.94
     hundreds
    0.93
     posters
    0.92
     selections
    0.91
     entries
    0.91
     numerous
    0.91
    Activations Density 0.441%

    No Known Activations