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. 0-RES-JB
    6. 24070
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ol' with the number 9 in the middle

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ol"

    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
     Ascend
    -0.63
     CSI
    -0.62
     Remastered
    -0.62
    SIGN
    -0.61
     Gemini
    -0.59
     UFOs
    -0.59
     Allied
    -0.58
     DRAG
    -0.58
     concerted
    -0.58
     Shinji
    -0.57
    POSITIVE LOGITS
    ol
    4.11
    ols
    2.52
    OL
    2.14
    olia
    2.05
    oling
    2.02
    olin
    1.92
    olate
    1.87
    oli
    1.86
    ole
    1.78
    oline
    1.78
    Activations Density 0.015%

    No Known Activations