Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4463
    Prev
    Next
    INDEX
    Explanations

    the prefix "dev" in words

    oai_token-act-pair · gpt-3.5-turbo

    variations of the term "dev" or "development."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ±
    -0.66
    xual
    -0.66
    ¿½
    -0.60
     Speedway
    -0.59
    zsche
    -0.59
     Weasley
    -0.57
     Moonlight
    -0.57
    ¦
    -0.57
     Highlander
    -0.56
     wait
    -0.56
    POSITIVE LOGITS
    olution
    1.35
    iant
    1.33
    olved
    1.30
    otional
    1.27
    iants
    1.27
    ouring
    1.26
    irtual
    1.25
    iating
    1.24
    otion
    1.21
    iation
    1.19
    Activations Density 0.020%

    No Known Activations