© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17366
    Prev
    Next
    INDEX
    Explanations

    advertisements within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "advertisement"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quartered
    -0.79
    bred
    -0.76
    velt
    -0.74
    venge
    -0.71
    ãĥĥãĥī
    -0.69
    »Ĵ
    -0.68
    uckle
    -0.68
    qs
    -0.67
    stood
    -0.67
    kens
    -0.66
    POSITIVE LOGITS
     Advertisement
    1.29
     Thumbnails
    0.86
    VERTISEMENT
    0.83
     Tickets
    0.77
     Policies
    0.77
     @@
    0.76
    vertising
    0.75
     âĶľâĶĢâĶĢ
    0.74
    advertisement
    0.72
     certs
    0.72
    Activations Density 0.007%

    No Known Activations