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. 5599
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-3.5-turbo

    syntax and structural elements typical in code or mathematical expressions

    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
    ModLoader
    -1.02
    ebus
    -0.76
    aldi
    -0.75
    aund
    -0.71
    76561
    -0.71
    rawdownloadcloneembedreportprint
    -0.70
    naire
    -0.69
     downtime
    -0.68
    Americ
    -0.67
    itech
    -0.67
    POSITIVE LOGITS
     [(
    0.90
    rolet
    0.82
     ',
    0.80
    âĪĴ
    0.80
     ((
    0.77
     fib
    0.75
     ",
    0.75
     constraint
    0.75
     theorem
    0.74
     algebra
    0.72
    Activations Density 0.081%

    No Known Activations