© 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. 8388
    Prev
    Next
    INDEX
    Explanations

    references to notable events or actions related to different fields, such as sports, politics, and entertainment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement or strong reactions in response to events

    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
     responsibly
    -0.69
    tenance
    -0.67
    eret
    -0.65
    é¾įå
    -0.65
     Applicant
    -0.64
     retains
    -0.63
    ardless
    -0.63
     moderation
    -0.62
     disadvantages
    -0.61
     latitude
    -0.61
    POSITIVE LOGITS
     exclaim
    1.35
     panic
    1.34
     shudder
    1.32
     panicked
    1.26
     incred
    1.25
     exclaimed
    1.23
     uproar
    1.23
     trem
    1.19
     disbelief
    1.17
     gasp
    1.17
    Activations Density 0.544%

    No Known Activations