© 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. 2-RES-JB
    11. 7562
    Prev
    Next
    INDEX
    Explanations

    names, especially the name "Matteo," and related terms like matte finishes and Philippe

    oai_token-act-pair · gpt-3.5-turbo

    terms related to finishes and textures, particularly matte finishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STON
    -0.87
    GBT
    -0.84
    Minnesota
    -0.81
    ARR
    -0.81
    ENTS
    -0.81
    UB
    -0.79
    District
    -0.78
    ruciating
    -0.78
    EEK
    -0.78
    OTE
    -0.77
    POSITIVE LOGITS
     Matte
    0.99
     paintings
    0.84
     painter
    0.84
     stripe
    0.80
     lipstick
    0.78
    ijn
    0.78
    chart
    0.76
     finish
    0.74
     painting
    0.74
     matte
    0.70
    Activations Density 0.015%

    No Known Activations