© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    numerical data such as rankings and statistics

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

    numerical data related to rankings or statistics

    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
    ¥ŀ
    -0.93
     tremend
    -0.85
    chwitz
    -0.82
     volunte
    -0.79
     millenn
    -0.77
     tradem
    -0.77
    GoldMagikarp
    -0.77
    inventoryQuantity
    -0.74
    anooga
    -0.74
    ongyang
    -0.73
    POSITIVE LOGITS
    95
    1.24
    97
    1.21
    96
    1.21
    85
    1.20
    62
    1.19
    93
    1.19
    87
    1.18
    94
    1.17
    75
    1.17
    72
    1.16
    Activations Density 0.173%

    No Known Activations