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. 4-RES-JB
    6. 21862
    Prev
    Next
    INDEX
    Explanations

    mentions of specific hospital names

    oai_token-act-pair · gpt-3.5-turbo

    references to hospitals and medical facilities

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

    No Comments

    Negative Logits
     sheet
    -0.86
    outed
    -0.75
     sheets
    -0.74
    heet
    -0.69
     blur
    -0.67
     moms
    -0.65
     aspiring
    -0.65
     literacy
    -0.64
     silence
    -0.62
    artist
    -0.62
    POSITIVE LOGITS
     District
    1.12
     Hotel
    1.07
     Plaza
    1.06
     Association
    1.01
     Complex
    0.98
     Parkway
    0.97
     Simulator
    0.97
     Partners
    0.96
     Authority
    0.95
     Trust
    0.95
    Activations Density 0.093%

    No Known Activations