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. 21918
    Prev
    Next
    INDEX
    Explanations

    complex words with multiple syllables related to difficulty or confusion

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to confusion or complexity around various issues

    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
     explorer
    -0.58
     Norn
    -0.58
     Annotations
    -0.51
     inspector
    -0.50
     examiner
    -0.50
     dates
    -0.49
     probe
    -0.49
    DragonMagazine
    -0.48
     oldest
    -0.48
     comma
    -0.47
    POSITIVE LOGITS
    ited
    0.81
    icked
    0.80
    vered
    0.80
    isted
    0.80
    posed
    0.77
    ivably
    0.75
    inged
    0.75
    istically
    0.75
    ashed
    0.75
    anted
    0.74
    Activations Density 0.576%

    No Known Activations