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. 8768
    Prev
    Next
    INDEX
    Explanations

    comparisons or emphasis on level or quality

    oai_token-act-pair · gpt-3.5-turbo

    comparisons or phrases emphasizing that something is greater or more significant than another

    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
     largeDownload
    -0.76
    CLASSIFIED
    -0.69
    ãģ®ç
    -0.65
     Juda
    -0.64
    EMENT
    -0.61
    NEY
    -0.60
     Direction
    -0.60
    ãĥ¡
    -0.60
    Winged
    -0.59
    ilic
    -0.59
    POSITIVE LOGITS
    whelming
    0.81
    atos
    0.76
     usual
    0.72
    vol
    0.67
    atever
    0.67
    usercontent
    0.66
    etheless
    0.65
    contact
    0.64
    represent
    0.63
    rel
    0.62
    Activations Density 0.087%

    No Known Activations