© 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. 9-RES-JB
    11. 10179
    Prev
    Next
    INDEX
    Explanations

    adverbs or adverbial phrases expressing certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    certainty and frequency in expressions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylum
    -0.72
     Mour
    -0.70
    forcing
    -0.61
     Wend
    -0.60
     needing
    -0.57
    forced
    -0.57
     Shaw
    -0.57
     Essential
    -0.56
     Mats
    -0.56
     fracturing
    -0.56
    POSITIVE LOGITS
     afford
    1.28
     manipulate
    1.00
     muster
    0.96
     imagine
    0.94
     withstand
    0.94
    handle
    0.93
     handle
    0.93
     convince
    0.92
     manage
    0.91
     capitalize
    0.90
    Activations Density 0.117%

    No Known Activations