© 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. 8-RES-JB
    11. 17260
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of clarity

    oai_token-act-pair · gpt-3.5-turbo

    text that expresses uncertainty or ambiguity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INT
    -0.82
    zig
    -0.78
    tha
    -0.75
    ocard
    -0.70
    clerosis
    -0.70
    jet
    -0.69
    tin
    -0.68
    ternity
    -0.66
    ITS
    -0.66
    FactoryReloaded
    -0.66
    POSITIVE LOGITS
     whether
    1.02
    ively
    0.81
     aloud
    0.78
    abouts
    0.77
    ether
    0.77
     how
    0.74
     jurisdiction
    0.72
     why
    0.70
    ly
    0.69
    whether
    0.69
    Activations Density 0.038%

    No Known Activations