© 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. 11-RES-JB
    11. 16335
    Prev
    Next
    INDEX
    Explanations

    phrases related to subscribing to newsletters

    oai_token-act-pair · gpt-3.5-turbo

    sign-up phrases for newsletters or updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.70
     borrowed
    -0.57
     derivatives
    -0.57
    RESULTS
    -0.55
    orsi
    -0.54
     ducks
    -0.54
     unseen
    -0.54
    Winged
    -0.54
     Uniform
    -0.53
     Minor
    -0.53
    POSITIVE LOGITS
    nai
    0.67
    ato
    0.64
    owder
    0.64
    NET
    0.61
    arna
    0.60
    etta
    0.59
    Balt
    0.59
    oola
    0.58
    biz
    0.58
    alde
    0.57
    Activations Density 0.038%

    No Known Activations