© 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. 8-RES-JB
    11. 19262
    Prev
    Next
    INDEX
    Explanations

    calls to action or requests for engagement such as visiting a website or signing a petition

    oai_token-act-pair · gpt-3.5-turbo

    actionable instructions and calls to action related to donations or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.68
     disadvant
    -0.61
     coupling
    -0.61
     overpowered
    -0.60
    pher
    -0.58
     inev
    -0.57
     apparent
    -0.56
     Gaw
    -0.56
    livious
    -0.56
    ushed
    -0.55
    POSITIVE LOGITS
     Email
    1.08
     Submit
    1.06
     Subscribe
    1.05
     subscribe
    1.00
     Website
    0.96
     Join
    0.94
     email
    0.92
    Email
    0.89
    Subscribe
    0.89
     bookmark
    0.87
    Activations Density 0.593%

    No Known Activations