© 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. 2008
    Prev
    Next
    INDEX
    Explanations

    words related to being unsurprised or unprepared for a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a lack of surprise regarding certain statements or outcomes

    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
    abase
    -0.87
    ngth
    -0.78
    sembly
    -0.76
     exting
    -0.73
    ictionary
    -0.73
     raft
    -0.73
    oreal
    -0.73
    ailability
    -0.72
    tein
    -0.72
    alach
    -0.69
    POSITIVE LOGITS
    DragonMagazine
    0.80
     anymore
    0.71
    imaru
    0.70
    actionDate
    0.70
     whatsoever
    0.69
     systemd
    0.69
    UFC
    0.65
    Notice
    0.65
     why
    0.65
     considering
    0.64
    Activations Density 0.047%

    No Known Activations