© 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 EvalsExportsinterp-engineNEWAPI 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. 11718
    Prev
    Next
    INDEX
    Explanations

    the word "Subscribe" in text

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts related to subscribing to content

    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
    esan
    -0.75
    cule
    -0.64
    come
    -0.64
     coh
    -0.64
    jas
    -0.62
     bil
    -0.62
    anca
    -0.62
    ball
    -0.62
    ilde
    -0.61
     glide
    -0.61
    POSITIVE LOGITS
     RSS
    0.89
     unsub
    0.86
    Subscribe
    0.80
     subscribe
    0.76
    Interstitial
    0.75
    ombat
    0.74
    scribe
    0.74
     subscriptions
    0.73
    henko
    0.71
     subscrib
    0.71
    Activations Density 0.029%

    No Known Activations