© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    titles or topics related to instructional or informative content

    oai_token-act-pair · gpt-3.5-turbo

    questions that begin with "How" or "Why."

    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
     meantime
    -0.70
    iHUD
    -0.70
    uther
    -0.66
     hereafter
    -0.65
     accordingly
    -0.64
    handedly
    -0.62
     wherever
    -0.62
    Interstitial
    -0.61
    aciously
    -0.60
    âĶĢ
    -0.60
    POSITIVE LOGITS
     Does
    1.29
     Did
    1.10
     Are
    1.07
     Should
    1.06
     Would
    1.05
     Didn
    1.01
     Could
    1.00
     Is
    0.99
     Were
    0.97
     Was
    0.96
    Activations Density 0.060%

    No Known Activations