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. 2472
    Prev
    Next
    INDEX
    Explanations

    Miscellaneous items and collections of related things

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating selection or aggregation of items or people

    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
    aeus
    -0.77
    imeter
    -0.74
    ared
    -0.72
    erate
    -0.71
    Reviewer
    -0.70
    ocene
    -0.70
    rome
    -0.67
    ipeg
    -0.66
    uca
    -0.66
    agall
    -0.64
    POSITIVE LOGITS
     goodies
    1.16
     assorted
    0.96
     items
    0.95
     notable
    0.91
     highlights
    0.91
     articles
    0.88
     extras
    0.88
     celebrities
    0.87
     appearances
    0.84
    cellaneous
    0.83
    Activations Density 0.334%

    No Known Activations