© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7300
    Prev
    Next
    INDEX
    Explanations

    keywords related to subscribing to receive emails, including news and promotions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to email subscriptions and newsletters

    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
     Murd
    -0.61
     tongues
    -0.60
     Shack
    -0.59
    Thumbnail
    -0.58
    geist
    -0.56
     halves
    -0.55
    lihood
    -0.55
     Crimes
    -0.55
     jaw
    -0.53
     Rothschild
    -0.52
    POSITIVE LOGITS
    ento
    0.75
    interstitial
    0.72
    )].
    0.61
    aturdays
    0.60
    ombies
    0.59
    DragonMagazine
    0.59
     externalToEVAOnly
    0.59
    aints
    0.58
    arez
    0.57
    ensual
    0.56
    Activations Density 0.056%

    No Known Activations