© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 24024
    Prev
    Next
    INDEX
    Explanations

    data related to statistics on various causes of death and health issues

    oai_token-act-pair · gpt-3.5-turbo

    statistics related to health-related incidents and their impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elight
    -0.67
     kindly
    -0.66
    Gam
    -0.65
     Gamer
    -0.64
    gradient
    -0.63
    escription
    -0.63
     confir
    -0.62
    cknow
    -0.61
     Option
    -0.61
    ãĤ¤ãĥĪ
    -0.59
    POSITIVE LOGITS
     annually
    1.49
     worldwide
    1.23
     yearly
    1.11
     globally
    1.09
     each
    1.09
    each
    0.98
     every
    0.97
     alone
    0.94
     Worldwide
    0.84
     annual
    0.84
    Activations Density 0.460%

    No Known Activations