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. 3415
    Prev
    Next
    INDEX
    Explanations

    gratitude and acknowledgment expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the word "first" in various contexts

    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
    etheless
    -1.00
    cffff
    -0.72
    sung
    -0.71
    atten
    -0.68
    laugh
    -0.68
    nes
    -0.68
    sports
    -0.68
    owl
    -0.66
    cel
    -0.65
    far
    -0.65
    POSITIVE LOGITS
     introdu
    1.03
    asma
    0.76
    ODUCT
    0.76
     assume
    0.67
     introduction
    0.67
     premise
    0.65
     assumption
    0.64
     Explain
    0.64
     disclaimer
    0.64
    ASY
    0.63
    Activations Density 0.294%

    No Known Activations