© 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. 6-RES-JB
    11. 12777
    Prev
    Next
    INDEX
    Explanations

    RSS feeds and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to RSS feeds and their related functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.88
    alkyrie
    -0.85
    itars
    -0.76
    pport
    -0.71
     submar
    -0.69
     exorc
    -0.68
     sworn
    -0.64
    isman
    -0.62
    inez
    -0.61
     Monstrous
    -0.61
    POSITIVE LOGITS
    feed
    1.19
     feeds
    1.10
    parser
    1.06
    lot
    0.97
     feed
    0.95
    stocks
    0.92
    vine
    0.90
     Feed
    0.90
    masters
    0.89
    forward
    0.85
    Activations Density 0.014%

    No Known Activations