© 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. 9-RES-JB
    11. 1703
    Prev
    Next
    INDEX
    Explanations

    phrases related to health risks and diseases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health risks and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.95
     largeDownload
    -0.87
    soDeliveryDate
    -0.86
    uably
    -0.82
    ĸļ
    -0.82
    minus
    -0.78
    notations
    -0.78
    arta
    -0.73
    å°Ĩ
    -0.73
    framework
    -0.72
    POSITIVE LOGITS
     illness
    1.29
     disease
    1.27
     cardiovascular
    1.21
     injury
    1.20
     infection
    1.20
     diseases
    1.19
     relapse
    1.12
     adverse
    1.11
     miscarriage
    1.10
     suicide
    1.08
    Activations Density 0.184%

    No Known Activations