© 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. 11-RES-JB
    11. 23149
    Prev
    Next
    INDEX
    Explanations

    questions or prompts starting with "So what" or "What" that introduce a topic or issue

    oai_token-act-pair · gpt-3.5-turbo

    questions that provoke inquiry or demand clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pione
    -0.85
    ñ
    -0.78
    Ļ½
    -0.76
    raphics
    -0.76
    ò
    -0.75
    ø
    -0.73
    č
    -0.72
    ö
    -0.72
    reportprint
    -0.72
    ù
    -0.72
    POSITIVE LOGITS
     exactly
    1.17
     does
    1.14
     happens
    1.02
     do
    1.01
     did
    0.93
     SHOULD
    0.90
     should
    0.88
     DOES
    0.87
     happened
    0.85
     can
    0.81
    Activations Density 0.069%

    No Known Activations