© 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. 6283
    Prev
    Next
    INDEX
    Explanations

    words related to increasing or adding to something, especially in a figurative sense

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate raising issues, questions, or adding new dimensions to discussions

    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
    owment
    -0.71
    icle
    -0.69
     behaves
    -0.65
     consisting
    -0.64
     proficient
    -0.63
    Percent
    -0.63
    ebted
    -0.63
     Referred
    -0.62
     Adapt
    -0.62
     behaved
    -0.62
    POSITIVE LOGITS
     doubts
    1.06
     uncertainty
    1.03
     suspicions
    1.02
     ammunition
    0.98
     impetus
    0.98
     urgency
    0.97
     doubt
    0.91
     scrutiny
    0.90
     uncertainties
    0.89
     credibility
    0.88
    Activations Density 0.200%

    No Known Activations