© 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. 5066
    Prev
    Next
    INDEX
    Explanations

    questions related to various topics and decision-making situations

    oai_token-act-pair · gpt-3.5-turbo

    questions and inquiries about processes or relationships, especially regarding communication and decision-making

    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
    onia
    -0.61
    orescence
    -0.59
    ICT
    -0.58
    FIELD
    -0.57
    ãĥģ
    -0.56
     laure
    -0.56
    inqu
    -0.54
    alky
    -0.53
    itual
    -0.52
    ouble
    -0.52
    POSITIVE LOGITS
     how
    1.80
     why
    1.68
    how
    1.61
    why
    1.58
    what
    1.47
     what
    1.47
     WHY
    1.46
     HOW
    1.43
     How
    1.39
     whence
    1.38
    Activations Density 0.296%

    No Known Activations