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. 2-RES-JB
    6. 19208
    Prev
    Next
    INDEX
    Explanations

    mentions of the specific name "Re"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Re" and its derivatives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.73
    DragonMagazine
    -0.72
     Nicarag
    -0.72
    åŃ
    -0.72
     CPC
    -0.70
     Icelandic
    -0.70
     Nieto
    -0.68
     Pebble
    -0.68
     Anchorage
    -0.68
     Northern
    -0.67
    POSITIVE LOGITS
    levant
    1.10
    becca
    1.07
    usable
    1.01
    asonable
    1.00
    acher
    1.00
    verend
    0.99
    uben
    0.98
    actor
    0.98
    asons
    0.97
    aches
    0.94
    Activations Density 0.015%

    No Known Activations