© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11593
    Prev
    Next
    INDEX
    Explanations

    time-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and references to time duration

    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
     Nietzsche
    -0.53
     Soros
    -0.52
     Sinn
    -0.52
     Macron
    -0.50
     Dru
    -0.50
     Wei
    -0.50
    ¶
    -0.50
     Plaintiff
    -0.49
     Sz
    -0.49
     Sut
    -0.48
    POSITIVE LOGITS
    iversary
    0.65
    ovation
    0.60
    accompan
    0.57
    itialized
    0.55
    oaded
    0.55
    roads
    0.54
    equal
    0.54
    vation
    0.52
    ouble
    0.51
    coming
    0.51
    Activations Density 1.619%

    No Known Activations