© 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. 2379
    Prev
    Next
    INDEX
    Explanations

    words related to conversations or competition

    oai_token-act-pair · gpt-3.5-turbo

    the word "vers" in various 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
     shower
    -0.63
     lodge
    -0.62
    endi
    -0.60
     discharge
    -0.59
     allot
    -0.58
     EntityItem
    -0.58
     Crab
    -0.58
     frog
    -0.57
     delim
    -0.57
    è¦ļéĨĴ
    -0.57
    POSITIVE LOGITS
    vers
    4.50
    VERS
    2.49
    ver
    1.92
    verse
    1.89
    VER
    1.75
    vert
    1.68
    Vers
    1.53
    ves
    1.49
    ving
    1.49
    vs
    1.41
    Activations Density 0.023%

    No Known Activations