© 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. 4-RES-JB
    11. 636
    Prev
    Next
    INDEX
    Explanations

    uncertainty or lack of clarity in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing ambiguity or uncertainty

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

    No Comments

    Negative Logits
    endar
    -0.84
    atra
    -0.83
    uld
    -0.82
    ocard
    -0.80
    INT
    -0.79
    onest
    -0.78
    uilding
    -0.77
    olon
    -0.76
    inse
    -0.75
    trak
    -0.74
    POSITIVE LOGITS
     chronological
    0.74
     wording
    0.68
     conflicting
    0.66
     regarding
    0.66
     unanimous
    0.65
     ambig
    0.65
     whether
    0.65
    icably
    0.65
    ly
    0.64
     borders
    0.64
    Activations Density 0.012%

    No Known Activations