© 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. 11351
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'To' indicating a call to action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts

    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
     yielded
    -0.67
    itates
    -0.65
     netted
    -0.61
    busters
    -0.60
     costing
    -0.60
     forg
    -0.59
    packing
    -0.58
    working
    -0.57
    craft
    -0.57
    itiz
    -0.56
    POSITIVE LOGITS
    ilet
    1.51
    pping
    1.13
    pped
    1.12
    ppings
    1.11
     summarize
    1.08
    asty
    1.06
    asted
    1.06
     paraph
    1.04
     clarify
    1.03
     reiterate
    1.03
    Activations Density 0.049%

    No Known Activations