© 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. 6-RES-JB
    11. 11924
    Prev
    Next
    INDEX
    Explanations

    language related to uncertainty and importance in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate uncertainty or unknown outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dumps
    -0.62
     AMA
    -0.62
     Kobe
    -0.59
     cafes
    -0.58
     Mak
    -0.57
     murders
    -0.57
     Mov
    -0.56
     oats
    -0.56
     bedrooms
    -0.55
    kay
    -0.52
    POSITIVE LOGITS
    etheless
    0.75
    ŃĶ
    0.73
    ?????-
    0.72
    ajor
    0.72
    HCR
    0.71
    IER
    0.71
    SourceFile
    0.70
    1027
    0.67
    Factor
    0.66
    oldown
    0.65
    Activations Density 0.672%

    No Known Activations