© 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. 22161
    Prev
    Next
    INDEX
    Explanations

    time-related words describing a duration or countdown

    oai_token-act-pair · gpt-3.5-turbo

    phrases mentioning "less than" followed by a numerical value

    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
    FH
    -0.66
    cean
    -0.64
    More
    -0.63
    aci
    -0.63
    ç«
    -0.63
    isson
    -0.63
    ier
    -0.62
    ãĥ¼ãĤ¯
    -0.62
    IED
    -0.62
    LOS
    -0.61
    POSITIVE LOGITS
     stellar
    1.08
     half
    0.95
     flattering
    0.93
     ideal
    0.92
     halfway
    0.91
     optimal
    0.89
     satisfactory
    0.85
     desirable
    0.82
     optimum
    0.81
    stellar
    0.81
    Activations Density 0.051%

    No Known Activations