© 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. 7863
    Prev
    Next
    INDEX
    Explanations

    disclosures about affiliate links and commissions in blog posts

    oai_token-act-pair · gpt-3.5-turbo

    references to affiliate links and associated financial disclosures

    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
     haste
    -0.68
     deportation
    -0.68
    itage
    -0.66
    panic
    -0.61
     Detention
    -0.59
     Forced
    -0.59
     detention
    -0.59
     Gork
    -0.58
     Opposition
    -0.57
    Fax
    -0.57
    POSITIVE LOGITS
     affiliate
    1.06
    iliate
    0.97
    azon
    0.84
     links
    0.83
     linking
    0.82
     advertis
    0.81
     purchases
    0.81
     sponsored
    0.77
     advertising
    0.77
     Disclosure
    0.77
    Activations Density 0.100%

    No Known Activations