© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a preference or an alternative course of action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "might as well."

    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
    arial
    -0.66
    ostic
    -0.64
    oresc
    -0.63
     Passing
    -0.63
    lining
    -0.60
    ories
    -0.59
    ãģ®å®
    -0.59
    ricting
    -0.58
    doms
    -0.57
    ãĤĮ
    -0.57
    POSITIVE LOGITS
     well
    1.12
    well
    0.90
    ivably
    0.86
    phy
    0.85
    lege
    0.84
     feas
    0.82
    nown
    0.80
     easily
    0.79
     plaus
    0.78
    pired
    0.78
    Activations Density 0.049%

    No Known Activations