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. 20149
    Prev
    Next
    INDEX
    Explanations

    mathematical and philosophical terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    complex philosophical concepts and discussions

    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
    lbs
    -0.75
     VIP
    -0.67
    Emergency
    -0.62
     rehab
    -0.62
     Jacksonville
    -0.58
     Championship
    -0.56
     booze
    -0.56
     Parkway
    -0.56
     Guys
    -0.55
    EED
    -0.55
    POSITIVE LOGITS
     philosophers
    1.01
     epist
    0.98
     empirical
    0.94
     eluc
    0.89
     philosoph
    0.86
     empir
    0.86
     normative
    0.85
     presupp
    0.85
     Chomsky
    0.85
     methodological
    0.84
    Activations Density 1.948%

    No Known Activations