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. 7351
    Prev
    Next
    INDEX
    Explanations

    words related to events happening at a specific time or related to a specific event

    oai_token-act-pair · gpt-3.5-turbo

    references to events or actions concerning an "it" or unspecified subjects

    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
    ãĥ³ãĤ¸
    -0.62
     revenge
    -0.60
     Guan
    -0.59
     lett
    -0.57
     privile
    -0.57
    ãģı
    -0.57
     powerless
    -0.57
     ashamed
    -0.56
     solitude
    -0.56
    cknow
    -0.56
    POSITIVE LOGITS
     debuted
    1.25
     premiered
    1.14
     surfaced
    0.95
     arrived
    0.92
     emerged
    0.90
     launches
    0.89
     appeared
    0.89
     expires
    0.88
     occurred
    0.86
     launched
    0.86
    Activations Density 0.215%

    No Known Activations