© 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. 6-RES-JB
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    calls to action or subscription-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email subscriptions and user notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appell
    -0.79
    eanor
    -0.78
    etheless
    -0.76
    urally
    -0.74
    livious
    -0.73
    SPONSORED
    -0.72
    affer
    -0.71
    urized
    -0.70
    uman
    -0.69
    asers
    -0.68
    POSITIVE LOGITS
    cgi
    0.74
    ãģ
    0.65
     auth
    0.65
     Spons
    0.64
     Search
    0.63
     subscribing
    0.61
     mins
    0.61
    oa
    0.60
     Cancel
    0.59
     text
    0.57
    Activations Density 0.059%

    No Known Activations