© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4591
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing 'or' with a high importance on the word 'or'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    repeated instances of the word "or" indicating alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Names
    -0.60
    final
    -0.60
    Course
    -0.60
    Characters
    -0.60
     Stability
    -0.58
    Enhanced
    -0.58
     Definitive
    -0.58
     Dimensions
    -0.57
     MID
    -0.57
    EN
    -0.56
    POSITIVE LOGITS
     hers
    0.94
     her
    0.88
    her
    0.86
    hers
    0.76
    chid
    0.76
    chard
    0.74
     herself
    0.74
    atory
    0.74
    leans
    0.72
    urga
    0.70
    Activations Density 0.027%

    No Known Activations