Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 18810
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to surprising or shocking events

    oai_token-act-pair · gpt-3.5-turbo

    words related to strong emotional reactions, particularly surprise and shock

    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
    porary
    -0.77
    wcsstore
    -0.64
    pleted
    -0.62
    urgy
    -0.61
    angible
    -0.61
    gins
    -0.61
    ©¶æ
    -0.61
    uts
    -0.60
    ãĥİ
    -0.60
     dimension
    -0.59
    POSITIVE LOGITS
     onlook
    1.32
     observers
    1.13
     me
    1.08
     us
    1.06
     readers
    1.05
     critics
    1.01
     audiences
    1.00
     viewers
    1.00
     everyone
    0.99
     regulators
    0.98
    Activations Density 0.133%

    No Known Activations