© 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. 13688
    Prev
    Next
    INDEX
    Explanations

    the word "should" in sentences expressing opinions or recommendations

    oai_token-act-pair · gpt-3.5-turbo

    the word "should" in various contexts related to recommendations or opinions

    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
     Fra
    -0.68
    fal
    -0.63
    GGGGGGGG
    -0.61
     ROS
    -0.61
    sein
    -0.61
    ZI
    -0.60
    quickShipAvailable
    -0.59
     Puzzle
    -0.59
    locked
    -0.59
     WI
    -0.58
    POSITIVE LOGITS
    ered
    1.09
     be
    1.03
    ering
    0.91
    bes
    0.84
     beware
    0.82
     aspire
    0.82
     strive
    0.82
    nt
    0.82
    n
    0.80
     ideally
    0.77
    Activations Density 0.069%

    No Known Activations