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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 15373
    Prev
    Next
    INDEX
    Explanations

    dates or time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or conditions that suggest infrequency or rarity

    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
     Cosponsors
    -0.62
     Kah
    -0.61
     FG
    -0.60
     Wilkinson
    -0.54
     Hes
    -0.53
     Grizzlies
    -0.53
     meanwhile
    -0.51
     VG
    -0.49
     Advertisement
    -0.48
     Gibraltar
    -0.48
    POSITIVE LOGITS
    natureconservancy
    0.64
    depending
    0.56
     coincidence
    0.54
    Closure
    0.50
    parent
    0.49
     begg
    0.47
    urgical
    0.47
     sibling
    0.46
    jri
    0.45
    daq
    0.45
    Activations Density 1.865%

    No Known Activations