© 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. 10-RES-JB
    11. 8594
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing information or instructions

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that introduce lists or enumerations

    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
    ãĥı
    -0.74
    ointed
    -0.61
    natureconservancy
    -0.58
    angering
    -0.58
    roud
    -0.56
    hya
    -0.55
    ãĤ¹ãĥĪ
    -0.55
    cill
    -0.54
     Ern
    -0.54
    ãĥ¼ãĥĨ
    -0.54
    POSITIVE LOGITS
     are
    0.96
     Thumbnails
    0.92
    neath
    0.87
     is
    0.86
    ground
    0.80
     summarizes
    0.79
    allery
    0.77
     depicts
    0.74
     screenshot
    0.74
    above
    0.71
    Activations Density 0.042%

    No Known Activations