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. 15388
    Prev
    Next
    INDEX
    Explanations

    terms related to academic qualifications, particularly undergraduate studies, and physical arm injuries, specifically related to the elbow

    oai_token-act-pair · gpt-3.5-turbo

    references to education and physical injuries, particularly related to undergraduate programs and elbow injuries

    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
    arde
    -0.82
    ularity
    -0.80
    Score
    -0.80
    hett
    -0.79
    aver
    -0.79
    ota
    -0.77
    leader
    -0.75
    ingham
    -0.73
    box
    -0.72
    reens
    -0.72
    POSITIVE LOGITS
    uates
    1.07
     grease
    0.89
    xual
    0.82
    culosis
    0.73
    icals
    0.69
    ses
    0.68
    æĢ
    0.67
    ohyd
    0.66
     plumbing
    0.63
     melan
    0.63
    Activations Density 0.054%

    No Known Activations