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. 9-RES-JB
    6. 10924
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    the word "about" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rift
    -0.80
    hesis
    -0.78
    chnology
    -0.78
    ãĤ¿
    -0.73
    quez
    -0.73
    åĽ
    -0.72
    terness
    -0.71
    GV
    -0.69
    ni
    -0.68
    chen
    -0.68
    POSITIVE LOGITS
     how
    0.85
     overcoming
    0.78
     reforming
    0.78
     halfway
    0.74
     conquering
    0.70
     topics
    0.67
     needing
    0.64
     hating
    0.64
     homosexuality
    0.64
     missing
    0.63
    Activations Density 0.108%

    No Known Activations