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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4652
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the abbreviation "Ne" followed by a number, such as "Ne 9" or "Ne 10"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Ne" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    -0.92
    ãĥ¼ãĥĨãĤ£
    -0.92
    DragonMagazine
    -0.91
    DOWN
    -0.86
    displayText
    -0.85
    MODE
    -0.85
    å§«
    -0.80
    REAM
    -0.79
    Ranked
    -0.78
    loo
    -0.77
    POSITIVE LOGITS
    arest
    1.05
    uron
    1.01
    elin
    0.98
    oliberal
    0.98
    olithic
    0.95
    ulia
    0.91
    cker
    0.90
    uter
    0.87
     Ne
    0.85
    ocom
    0.82
    Activations Density 0.006%

    No Known Activations