© 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. 4-RES-JB
    11. 493
    Prev
    Next
    INDEX
    Explanations

    sentences ending with a specific symbol or punctuation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "Ms." followed by names

    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
    ãĥ¼ãĥĨ
    -0.82
     dams
    -0.77
     eleph
    -0.75
     roundup
    -0.68
    ÃĥÃĤ
    -0.67
     nexus
    -0.67
    ebook
    -0.67
    adiator
    -0.66
    obyl
    -0.66
     prin
    -0.65
    POSITIVE LOGITS
     Jill
    0.75
    ItemTracker
    0.70
     Inqu
    0.70
    agger
    0.69
    assetsadobe
    0.65
    76561
    0.64
     Hawking
    0.64
     Chal
    0.63
     Carol
    0.62
     McH
    0.61
    Activations Density 0.029%

    No Known Activations