© 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. 1766
    Prev
    Next
    INDEX
    Explanations

    phrases related to requests or demands

    oai_token-act-pair · gpt-3.5-turbo

    references to demands or calls for action

    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
    encies
    -0.74
    pires
    -0.72
     inadvertently
    -0.64
     unwittingly
    -0.61
     luckily
    -0.61
    olph
    -0.61
     annoy
    -0.60
    nown
    -0.60
     habits
    -0.60
     dots
    -0.60
    POSITIVE LOGITS
     rethink
    1.30
     halt
    1.28
     boycott
    1.27
     moratorium
    1.27
     apology
    1.17
     recount
    1.17
     reconsider
    1.13
     ban
    1.05
     clarification
    1.04
     refund
    1.02
    Activations Density 0.177%

    No Known Activations