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. 15543
    Prev
    Next
    INDEX
    Explanations

    verbs related to taking action and making changes

    oai_token-act-pair · gpt-3.5-turbo

    action verbs that indicate teaching, responsibility, and engagement

    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
     skew
    -0.65
    rawdownloadcloneembedreportprint
    -0.64
     wraps
    -0.59
    nih
    -0.59
    ItemTracker
    -0.59
     wont
    -0.56
     Duff
    -0.56
     dab
    -0.56
     microscope
    -0.54
    rous
    -0.54
    POSITIVE LOGITS
     oneself
    1.03
     RELEASE
    0.90
    igl
    0.79
    yne
    0.73
    ANGE
    0.71
     Anxiety
    0.71
    ardless
    0.70
    FIX
    0.68
    itate
    0.68
    ISE
    0.66
    Activations Density 0.337%

    No Known Activations