© 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. 8-RES-JB
    11. 22293
    Prev
    Next
    INDEX
    Explanations

    countries or regions

    oai_token-act-pair · gpt-3.5-turbo

    names of specific countries, states, and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.66
    visory
    -0.65
     Berm
    -0.59
    uminati
    -0.57
     Emin
    -0.56
    tones
    -0.56
     booth
    -0.55
    ibus
    -0.54
    reviewed
    -0.54
    ebin
    -0.54
    POSITIVE LOGITS
     itself
    0.84
    's
    0.79
     lacks
    0.73
    ians
    0.72
     stagn
    0.72
     suffers
    0.72
     succeeds
    0.72
    ans
    0.72
    mania
    0.71
     loses
    0.71
    Activations Density 0.274%

    No Known Activations