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. 14286
    Prev
    Next
    INDEX
    Explanations

    sequences representing specific characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and data references

    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
    itory
    -0.73
    itionally
    -0.68
     Beir
    -0.66
    arians
    -0.66
    ãĥ¤
    -0.65
    acements
    -0.64
    icas
    -0.63
    ipation
    -0.63
     EntityItem
    -0.62
    imaru
    -0.62
    POSITIVE LOGITS
    teenth
    1.43
    teen
    1.35
    th
    0.96
    34
    0.90
    36
    0.89
     months
    0.86
    04
    0.86
    03
    0.85
    012
    0.85
    018
    0.85
    Activations Density 0.097%

    No Known Activations