© 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. 7-RES-JB
    11. 2092
    Prev
    Next
    INDEX
    Explanations

    numerical mentions of people or groups

    oai_token-act-pair · gpt-3.5-turbo

    numbers indicating large quantities of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opia
    -0.87
    ãĤ¦ãĤ¹
    -0.81
    Favorite
    -0.72
    livion
    -0.72
     immortality
    -0.70
    fusc
    -0.66
    Url
    -0.66
    ensis
    -0.65
    Own
    -0.64
    ãĤ´ãĥ³
    -0.63
    POSITIVE LOGITS
     mourn
    0.99
     protesters
    0.90
     demonstrators
    0.88
     wounded
    0.82
     arrests
    0.80
     activists
    0.79
     observers
    0.79
     died
    0.78
     casualties
    0.78
     masked
    0.77
    Activations Density 0.281%

    No Known Activations