© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    phrases or terms associated with instructions or commands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "right now."

    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
    è¦ļéĨĴ
    -0.66
     cellul
    -0.64
    raved
    -0.64
     Remastered
    -0.64
    arette
    -0.62
     Railroad
    -0.60
    aples
    -0.57
    odium
    -0.57
    ITED
    -0.57
    idated
    -0.56
    POSITIVE LOGITS
    eous
    1.29
     now
    0.97
     wing
    0.87
     smack
    0.84
     fielder
    0.83
    move
    0.82
    wing
    0.82
     away
    0.77
     winger
    0.76
     tackle
    0.72
    Activations Density 0.034%

    No Known Activations