© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2293
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscriptions and opt-outs

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to subscription services and user agreements

    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
     Shack
    -0.58
     Murd
    -0.58
     brut
    -0.52
     Bord
    -0.52
     Shelter
    -0.51
     Widow
    -0.51
     Mansion
    -0.51
     Formation
    -0.51
     robbers
    -0.51
     Barber
    -0.50
    POSITIVE LOGITS
    Interstitial
    0.83
    interstitial
    0.75
     subscribing
    0.70
     Thumbnails
    0.60
     subscriptions
    0.60
    ":[
    0.59
    DragonMagazine
    0.59
    ás
    0.58
    ctory
    0.58
    vernight
    0.58
    Activations Density 0.039%

    No Known Activations