© 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. 10-RES-JB
    11. 13697
    Prev
    Next
    INDEX
    Explanations

    phrases related to future plans, updates, and releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions or limitations related to product offerings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¬¼
    -0.72
    iuses
    -0.71
    rived
    -0.67
    ocaust
    -0.65
    ĸļ
    -0.64
    seless
    -0.64
     invaded
    -0.64
    azo
    -0.64
     glor
    -0.63
    opped
    -0.63
    POSITIVE LOGITS
     hopefully
    1.14
     Plans
    1.08
     Expect
    1.05
     anticip
    1.04
     Stay
    1.03
     TBD
    1.03
    will
    0.99
     Updates
    0.97
     Hopefully
    0.97
     plans
    0.95
    Activations Density 0.518%

    No Known Activations