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. 23232
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various industries and sectors, including entertainment, healthcare, finance, and public service

    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
    alle
    -0.62
    é¾įå
    -0.60
    ãĤ¨ãĥ«
    -0.56
    ãĤ®
    -0.53
    ãĤ½
    -0.53
    itional
    -0.53
    Versions
    -0.52
    inarily
    -0.52
    ãģĦ
    -0.50
    ãĥ¼ãĥĨ
    -0.50
    POSITIVE LOGITS
     championed
    0.52
     (#
    0.52
     circa
    0.49
    ¯
    0.49
    =-=-=-=-
    0.49
     (.
    0.49
    âĢİ
    0.48
     (
    0.47
     aka
    0.47
     ($
    0.47
    Activations Density 1.031%

    No Known Activations