© 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. 7532
    Prev
    Next
    INDEX
    Explanations

    phrases containing the contraction "you're"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "to be" in different contexts

    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
    ËĪ
    -0.67
    mination
    -0.64
    anguages
    -0.61
     dismant
    -0.60
    esa
    -0.60
    obbies
    -0.59
     lengths
    -0.59
    ipal
    -0.59
    angles
    -0.58
    abor
    -0.58
    POSITIVE LOGITS
     welcome
    1.28
     kidding
    1.01
     gonna
    1.00
     probably
    0.96
     hereby
    0.92
     forgiven
    0.90
     lucky
    0.89
     wasting
    0.88
     entitled
    0.87
     forgetting
    0.87
    Activations Density 0.145%

    No Known Activations