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. 5953
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to laws and legal concepts

    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
    eki
    -0.88
    ĸļ
    -0.75
    omo
    -0.73
    zik
    -0.68
    olulu
    -0.67
    bye
    -0.67
     mog
    -0.67
     Merrill
    -0.67
     hurd
    -0.66
     helicop
    -0.66
    POSITIVE LOGITS
    ensical
    1.00
    rences
    0.85
    runtime
    0.83
    å§«
    0.75
    \">
    0.69
     Uncommon
    0.69
    ãĥĥãĥī
    0.67
    rities
    0.67
    aceae
    0.67
    ãĤ¶
    0.64
    Activations Density 0.131%

    No Known Activations