© 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 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. 4322
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making or facing difficult choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases or elements indicating likelihood or possibility

    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
    sburgh
    -0.78
    okes
    -0.67
    usalem
    -0.65
    tx
    -0.65
    rete
    -0.64
    ammad
    -0.63
    jong
    -0.62
    andise
    -0.60
    alse
    -0.60
     chaired
    -0.60
    POSITIVE LOGITS
     possibility
    1.78
     prospect
    1.41
     notion
    1.37
     temptation
    1.31
     slightest
    1.30
     impression
    1.29
     idea
    1.28
     occasional
    1.23
     assumption
    1.22
     realization
    1.19
    Activations Density 0.268%

    No Known Activations