© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18102
    Prev
    Next
    INDEX
    Explanations

    specific words related to the term "ophon"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names or terms related to broadcasting or media

    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
    ILLE
    -0.82
    Äĩ
    -0.67
     paranormal
    -0.67
     Turtles
    -0.64
    wolf
    -0.62
     Game
    -0.62
     Catholicism
    -0.61
    microsoft
    -0.60
     Leafs
    -0.60
     Penguins
    -0.60
    POSITIVE LOGITS
    ophon
    4.12
    odynam
    0.96
    odynamic
    0.82
    ouver
    0.79
    heng
    0.78
     ................
    0.77
     Tact
    0.74
    ORGE
    0.72
     Treasurer
    0.72
     Mn
    0.71
    Activations Density 0.015%

    No Known Activations