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. 2092
    Prev
    Next
    INDEX
    Explanations

    words related to registration and sign-up processes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "register" and its variants

    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
    wich
    -0.74
    ilitarian
    -0.69
    Ľ
    -0.69
    adelphia
    -0.68
    Sax
    -0.66
    pei
    -0.65
    yg
    -0.65
     Lanka
    -0.64
    jay
    -0.64
    Īè
    -0.64
    POSITIVE LOGITS
    ifications
    0.89
    ifying
    0.89
    ifiers
    0.77
    keepers
    0.74
    essional
    0.72
    ify
    0.72
    ifier
    0.71
    ifiable
    0.71
    register
    0.71
    emark
    0.71
    Activations Density 0.015%

    No Known Activations