© 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. 4-RES-JB
    11. 20440
    Prev
    Next
    INDEX
    Explanations

    words related to professions or careers

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with making a living or achieving personal goals

    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
     marriages
    -0.57
    furt
    -0.54
     pairs
    -0.53
     Convers
    -0.52
     Canaveral
    -0.50
     obser
    -0.49
     households
    -0.49
     Alban
    -0.48
    ãĤ¼
    -0.48
     Procedures
    -0.48
    POSITIVE LOGITS
    liest
    0.74
    iest
    0.69
    elight
    0.68
    hole
    0.66
     shine
    0.62
    est
    0.60
    emaker
    0.59
    ARDIS
    0.57
    holes
    0.57
    cloth
    0.56
    Activations Density 0.417%

    No Known Activations