© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8995
    Prev
    Next
    INDEX
    Explanations

    advertisements within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements or promotional content

    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
    borg
    -0.78
    ties
    -0.69
    venge
    -0.69
    meal
    -0.68
    stood
    -0.68
    lich
    -0.66
    elf
    -0.64
    velt
    -0.64
    bred
    -0.63
    krit
    -0.63
    POSITIVE LOGITS
     Advertisement
    0.88
     Thumbnails
    0.87
    advertisement
    0.85
    Item
    0.82
     <!--
    0.80
    etitive
    0.77
    ļéĨĴ
    0.77
    inson
    0.76
    WithNo
    0.75
     @@
    0.73
    Activations Density 0.028%

    No Known Activations