© 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. 7-RES-JB
    11. 23837
    Prev
    Next
    INDEX
    Explanations

    instances of the word "surely" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    the word "surely" and its variations in various contexts suggesting certainty or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.87
    arthed
    -0.78
    insula
    -0.78
    psey
    -0.77
    iatus
    -0.75
    entary
    -0.71
    NING
    -0.70
    anwhile
    -0.69
    apsed
    -0.66
    rition
    -0.66
    POSITIVE LOGITS
     someday
    0.83
    è¦
    0.72
     ought
    0.67
     deserved
    0.66
    footed
    0.66
     deserve
    0.65
     nud
    0.64
     await
    0.63
     surpass
    0.62
     deserves
    0.62
    Activations Density 0.029%

    No Known Activations