© 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. 5241
    Prev
    Next
    INDEX
    Explanations

    questions related to actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with punctuation indicating a question or exclamation

    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
    ãĥ«
    -0.65
    ometry
    -0.64
    tin
    -0.61
    ãĥĭ
    -0.59
    ciplinary
    -0.58
    ãĥķãĤ¡
    -0.57
     reven
    -0.57
    Desktop
    -0.56
    amas
    -0.56
    ucket
    -0.56
    POSITIVE LOGITS
    /"
    1.01
     Then
    0.99
     Nope
    0.91
     Later
    0.88
     etc
    0.87
     followed
    0.86
     And
    0.86
     whereas
    0.85
     Suddenly
    0.85
     Immediately
    0.85
    Activations Density 0.097%

    No Known Activations