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. 8-RES-JB
    6. 7509
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possibility or potential

    oai_token-act-pair · gpt-3.5-turbo

    expressions of possibility or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ament
    -0.79
     Lauder
    -0.73
    cies
    -0.72
     Constant
    -0.71
    oric
    -0.66
    heid
    -0.63
    rett
    -0.61
    breeding
    -0.61
    raint
    -0.59
    feeding
    -0.59
    POSITIVE LOGITS
     someday
    1.11
    ily
    1.02
     feas
    1.02
     conce
    0.99
     be
    0.96
    haps
    0.91
     offend
    0.89
     inadvertently
    0.87
     plaus
    0.87
    onna
    0.86
    Activations Density 0.058%

    No Known Activations