Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 8000
    Prev
    Next
    INDEX
    Explanations

    consecutive texts containing the word "resort" followed by a verb ending in 'ing'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resort" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hemat
    -0.70
    rod
    -0.69
    APH
    -0.63
    arkin
    -0.61
    warm
    -0.61
    ector
    -0.59
    corn
    -0.58
    older
    -0.58
    chrom
    -0.58
    MAT
    -0.58
    POSITIVE LOGITS
     resorts
    0.85
     resort
    0.84
    geoning
    0.79
    ulic
    0.77
    urous
    0.74
     Resort
    0.72
    uations
    0.71
    itution
    0.70
    reality
    0.69
    itous
    0.69
    Activations Density 0.018%

    No Known Activations