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. 4486
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of agreement or consensus expressed in the text

    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
    akin
    -0.78
    chin
    -0.71
     Dise
    -0.70
    quer
    -0.68
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    ornia
    -0.65
     netted
    -0.65
    Scope
    -0.62
    phy
    -0.62
     ponds
    -0.62
    POSITIVE LOGITS
     regards
    1.10
     regard
    1.01
     respect
    0.84
    standing
    0.78
    ĪĴ
    0.73
    hus
    0.71
    asper
    0.70
    stood
    0.67
     unanimous
    0.64
     them
    0.64
    Activations Density 0.061%

    No Known Activations