© 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 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. 10-RES-JB
    11. 3357
    Prev
    Next
    INDEX
    Explanations

    phrases related to advertising or promotions

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that indicate the continuation of stories or advertisements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bage
    -0.61
    è¦ļéĨĴ
    -0.58
    Pri
    -0.57
    hol
    -0.57
    crit
    -0.56
    Range
    -0.55
    venge
    -0.55
    liest
    -0.55
     Bows
    -0.55
    Writ
    -0.53
    POSITIVE LOGITS
     advertisement
    1.05
     slideshow
    0.79
    imeo
    0.78
    igon
    0.78
     Advertisement
    0.67
     Thumbnails
    0.65
     âĨ
    0.62
     gallery
    0.62
    ebin
    0.61
     Gallery
    0.60
    Activations Density 0.011%

    No Known Activations