© 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. 0-RES-JB
    11. 5295
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ot' followed by the number 9

    oai_token-act-pair · gpt-3.5-turbo

    references to "ot" in a variety of contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Painter
    -0.66
     playback
    -0.62
     hr
    -0.60
     inhibitors
    -0.59
     AUD
    -0.59
     âĢİ
    -0.58
     DRAGON
    -0.57
     feasibility
    -0.56
     Engels
    -0.56
     embargo
    -0.56
    POSITIVE LOGITS
    ot
    4.20
    ots
    2.70
    OT
    1.90
    ota
    1.84
    oter
    1.77
    ote
    1.72
    otin
    1.71
    oting
    1.65
    otes
    1.62
    oton
    1.62
    Activations Density 0.018%

    No Known Activations