© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 6432
    Prev
    Next
    INDEX
    Explanations

    hashtags and social media profile names

    oai_token-act-pair · gpt-3.5-turbo

    references to names and numerical identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Abby
    -0.90
     Mug
    -0.87
     Aman
    -0.86
    ð
    -0.83
     Asgard
    -0.80
     Morg
    -0.78
     AAA
    -0.77
     ACPI
    -0.76
     Vulkan
    -0.76
     toast
    -0.75
    POSITIVE LOGITS
    LE
    1.33
    Le
    1.23
     LE
    1.23
    le
    1.22
    leon
    1.20
    eele
    1.18
     Lei
    1.14
     Lep
    1.11
     Kle
    1.11
    ILE
    1.09
    Activations Density 0.442%

    No Known Activations