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. 12-RES-JB
    6. 15057
    Prev
    Next
    INDEX
    Explanations

    information related to weekend events and scheduled timings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases and a variety of contextual references to technology and digital communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ANE
    -0.65
    jay
    -0.64
    ayan
    -0.63
     ãĤ
    -0.62
    anz
    -0.61
    Trivia
    -0.61
    ellen
    -0.59
    ans
    -0.58
     BELOW
    -0.57
     Citiz
    -0.55
    POSITIVE LOGITS
    standing
    0.65
     mold
    0.63
     mould
    0.62
    fired
    0.61
    socket
    0.60
    rise
    0.60
    grad
    0.60
    ersed
    0.60
    ended
    0.59
    empt
    0.57
    Activations Density 0.374%

    No Known Activations