Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 2484
    Prev
    Next
    INDEX
    Explanations

    the prefix "pr" followed by a high numerical value, possibly indicating importance or priority

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "pr" likely related to "press" or "public relations."

    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
     Dwarf
    -0.74
     Wand
    -0.73
     Cheong
    -0.70
    querque
    -0.67
    liner
    -0.64
     EntityItem
    -0.64
     Druid
    -0.62
    STER
    -0.61
    riad
    -0.61
    erness
    -0.61
    POSITIVE LOGITS
    udence
    1.17
    ODUCT
    1.05
    atche
    1.01
    ayer
    1.00
    istine
    0.99
    inters
    0.99
    icing
    0.99
    acking
    0.93
    ayed
    0.92
    anded
    0.92
    Activations Density 0.009%

    No Known Activations