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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 4529
    Prev
    Next
    INDEX
    Explanations

    chemical compounds related to phosphorus

    oai_token-act-pair · gpt-3.5-turbo

    special symbols and characters, possibly indicating formatting or specific encoding in the text

    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
     Leilan
    -0.69
    ilater
    -0.67
     Yankee
    -0.66
     Myster
    -0.66
     Cosponsors
    -0.65
    ffen
    -0.63
     Gap
    -0.62
     Franch
    -0.62
    DragonMagazine
    -0.61
     WOR
    -0.60
    POSITIVE LOGITS
    ´
    1.48
    ²
    1.47
    Į
    1.42
    ¸
    1.41
    ¦
    1.37
    Ń
    1.37
    º
    1.37
    £
    1.36
    °
    1.33
    «
    1.33
    Activations Density 0.010%

    No Known Activations