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. 11066
    Prev
    Next
    INDEX
    Explanations

    sequential numbers or dates

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and statistics related to various topics

    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
     skelet
    -0.64
     UNCLASSIFIED
    -0.61
     exting
    -0.58
     disadvant
    -0.57
    âķIJ
    -0.57
    CONCLUS
    -0.55
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.53
    Conclusion
    -0.53
     pse
    -0.53
     welf
    -0.52
    POSITIVE LOGITS
     [â̦]
    0.66
     âĢİ
    0.62
    âĢİ
    0.59
     Posted
    0.56
    20439
    0.53
     âĢº
    0.53
     Donald
    0.49
     frontman
    0.48
     Thursday
    0.48
     cryptocurrency
    0.47
    Activations Density 5.818%

    No Known Activations