© 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. 10-RES-JB
    11. 10521
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and business

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oil, work, and development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haram
    -0.66
     reper
    -0.64
     pleading
    -0.61
     rehab
    -0.55
    XM
    -0.54
     breathing
    -0.54
    channelAvailability
    -0.54
     constitu
    -0.53
     orphan
    -0.53
     fiat
    -0.52
    POSITIVE LOGITS
    ers
    3.06
    er
    2.73
    ership
    2.30
    ERS
    1.99
    ering
    1.88
    ER
    1.85
    ery
    1.69
    ered
    1.69
    erness
    1.63
    erd
    1.57
    Activations Density 0.238%

    No Known Activations