© 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. 9-RES-JB
    11. 10153
    Prev
    Next
    INDEX
    Explanations

    mentions of new releases, products, or updates

    oai_token-act-pair · gpt-3.5-turbo

    promotional phrases for new products or releases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akespeare
    -0.91
     telephone
    -0.83
     newspapers
    -0.82
    fax
    -0.77
     cler
    -0.76
    Wikipedia
    -0.75
     administrations
    -0.75
    Journal
    -0.74
    kefeller
    -0.74
     funer
    -0.72
    POSITIVE LOGITS
     newcomer
    1.07
     debut
    0.98
     newest
    0.97
     Rampage
    0.94
     Kraken
    0.89
     upcoming
    0.89
    senal
    0.88
     sophomore
    0.88
     Spectre
    0.87
     Toro
    0.87
    Activations Density 0.656%

    No Known Activations