© 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. 10-RES-JB
    11. 8350
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty and questioning

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty and questioning

    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
     varies
    -0.73
     observes
    -0.69
    enary
    -0.67
    licts
    -0.65
    erity
    -0.64
     ensures
    -0.64
     warns
    -0.63
     remains
    -0.62
    oÄŁan
    -0.62
    zens
    -0.61
    POSITIVE LOGITS
     mattered
    0.77
     needed
    0.75
     wanted
    0.74
    anything
    0.69
     WAS
    0.67
     sounded
    0.65
     possibilities
    0.65
     belonged
    0.65
     outwe
    0.64
     existed
    0.64
    Activations Density 0.779%

    No Known Activations