© 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. 6575
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email newsletters and subscription content

    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
    aft
    -0.70
     Patriarch
    -0.66
    bach
    -0.64
    skinned
    -0.62
    fig
    -0.61
     Aram
    -0.61
    rers
    -0.59
     Ath
    -0.58
    POR
    -0.56
    peg
    -0.56
    POSITIVE LOGITS
     Subscribe
    1.04
     inbox
    0.79
    allery
    0.78
    ombat
    0.71
    email
    0.70
     Dragonbound
    0.70
    helle
    0.68
    ategor
    0.66
    antha
    0.65
    esy
    0.64
    Activations Density 0.022%

    No Known Activations