© 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. 13769
    Prev
    Next
    INDEX
    Explanations

    the word "or" in the context of making decisions or presenting options

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "whether or not"

    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
    Tes
    -0.60
     throats
    -0.59
     Scrib
    -0.53
     Tec
    -0.50
    enegger
    -0.50
    Pros
    -0.49
     Scenes
    -0.49
     Translation
    -0.49
    Sum
    -0.49
     Pony
    -0.48
    POSITIVE LOGITS
    nam
    0.83
    not
    0.80
     not
    0.73
    acles
    0.70
    ifice
    0.68
    adic
    0.67
    å¦
    0.66
    Else
    0.66
     NOT
    0.66
    any
    0.63
    Activations Density 0.019%

    No Known Activations