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. 7816
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming languages

    oai_token-act-pair · gpt-3.5-turbo

    references to programming languages and notable figures or entities associated with them

    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
    eatures
    -0.80
     Ezek
    -0.72
     Adin
    -0.69
    ocol
    -0.68
    ients
    -0.68
     Stam
    -0.66
     Seat
    -0.65
     Nanto
    -0.65
    uckland
    -0.64
    ccording
    -0.63
    POSITIVE LOGITS
     bombshell
    0.73
     famously
    0.72
    ®
    0.71
    sburg
    0.71
     frontman
    0.69
    ®,
    0.69
     lyrics
    0.68
    âĦ¢
    0.66
     Lite
    0.65
     novels
    0.64
    Activations Density 0.525%

    No Known Activations