© 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. 3-RES-JB
    11. 15115
    Prev
    Next
    INDEX
    Explanations

    hospital-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to hospitals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Helpful
    -0.76
    lass
    -0.73
    yip
    -0.73
    artisan
    -0.72
    BOOK
    -0.71
    AUT
    -0.67
    */(
    -0.67
    wcsstore
    -0.66
    xit
    -0.65
    xual
    -0.65
    POSITIVE LOGITS
    ilitating
    0.86
     annex
    0.83
    opath
    0.82
     outpatient
    0.82
     hospital
    0.80
    itals
    0.79
    bed
    0.76
    ization
    0.75
     patients
    0.74
     evacuation
    0.74
    Activations Density 0.017%

    No Known Activations