© 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. 9-RES-JB
    11. 10144
    Prev
    Next
    INDEX
    Explanations

    email-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to email communication and subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aroo
    -0.65
     Shack
    -0.57
    nor
    -0.57
     dracon
    -0.57
     Dracula
    -0.56
     Hood
    -0.54
     fanatic
    -0.54
    lihood
    -0.53
    lust
    -0.53
    NAS
    -0.52
    POSITIVE LOGITS
     newsletters
    0.78
     containing
    0.74
    pload
    0.74
     externalToEVAOnly
    0.74
    interstitial
    0.71
     newsletter
    0.69
    PsyNetMessage
    0.69
    DragonMagazine
    0.68
    email
    0.67
     subscribing
    0.65
    Activations Density 0.027%

    No Known Activations