© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 24014
    Prev
    Next
    INDEX
    Explanations

    sponsored advertisement tags within text passages

    oai_token-act-pair · gpt-3.5-turbo

    instances of advertisements in the text

    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
    ãĥ¼ãĥĨãĤ£
    -0.64
     HMS
    -0.61
    grass
    -0.60
     Roses
    -0.59
     Ultr
    -0.58
     Bounty
    -0.56
    pled
    -0.55
     Shib
    -0.55
     Discord
    -0.54
     fasc
    -0.54
    POSITIVE LOGITS
    Skip
    1.06
    ADVERTISEMENT
    0.88
     Thanks
    0.79
    zbollah
    0.73
    sylvania
    0.70
    sburgh
    0.68
    iciary
    0.68
    osi
    0.67
    acia
    0.64
    inarily
    0.64
    Activations Density 0.023%

    No Known Activations