© 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. 1-RES-JB
    11. 10204
    Prev
    Next
    INDEX
    Explanations

    references to large, influential companies, especially those in the realm of oil and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to large, influential companies or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    activated
    -0.79
    iring
    -0.78
    estate
    -0.77
    oral
    -0.77
    cise
    -0.74
    selection
    -0.74
    ople
    -0.72
    vere
    -0.71
    pt
    -0.69
    Ĵ
    -0.69
    POSITIVE LOGITS
     giants
    1.42
     titan
    1.06
    oliath
    0.93
    layer
    0.86
    osaurs
    0.86
     mammoth
    0.80
     jugg
    0.77
    paces
    0.76
     angel
    0.75
     beasts
    0.74
    Activations Density 0.012%

    No Known Activations