© 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 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. 6147
    Prev
    Next
    INDEX
    Explanations

    instructions or conditions related to actions, requests, or permissions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements involving the word "you."

    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
    Topics
    -0.67
    ãĥ´
    -0.66
    none
    -0.65
     unanswered
    -0.61
    NetMessage
    -0.60
    favorite
    -0.60
    Topic
    -0.60
     understatement
    -0.60
    ãĥ³
    -0.59
     remaining
    -0.59
    POSITIVE LOGITS
     explicitly
    1.14
     expressly
    1.13
     specifically
    1.00
     somehow
    0.90
     absolutely
    0.84
     accompanied
    0.84
     urgently
    0.83
     specially
    0.81
     otherwise
    0.79
     individually
    0.78
    Activations Density 0.122%

    No Known Activations