© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    web-related terms and calls to action typically found in website footers or newsletter sign-up sections

    oai_token-act-pair · gpt-3.5-turbo

    content related to user engagement and subscription prompts

    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
    rador
    -0.64
    bons
    -0.63
    rium
    -0.63
    rox
    -0.61
     largeDownload
    -0.60
    ndum
    -0.59
    RAM
    -0.57
     rehearsal
    -0.57
     Wonderland
    -0.56
     Clown
    -0.56
    POSITIVE LOGITS
    Subscribe
    0.77
     Cancel
    0.65
    Privacy
    0.65
     Subscribe
    0.64
     subscribing
    0.63
     adhere
    0.63
    settings
    0.62
    Month
    0.61
     domains
    0.61
    content
    0.59
    Activations Density 0.177%

    No Known Activations