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. 7-RES-JB
    6. 8447
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a degree of quality or judgment, such as "at best" or "at worst."

    oai_token-act-pair · gpt-3.5-turbo

    evaluations of quality or credibility, especially concerning something's reliability or truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kefeller
    -0.65
     favourite
    -0.64
     Mothers
    -0.64
     Prin
    -0.63
    men
    -0.62
    line
    -0.62
    aternity
    -0.62
    ussions
    -0.61
     clearance
    -0.61
     Favorite
    -0.60
    POSITIVE LOGITS
     glance
    0.84
     è£ıè
    0.75
     blush
    0.71
    chester
    0.71
     minim
    0.69
    aic
    0.64
    lehem
    0.64
     superf
    0.62
    ãĥīãĥ©ãĤ´ãĥ³
    0.62
    ctory
    0.62
    Activations Density 0.020%

    No Known Activations