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. 7738
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical abilities, particularly speed, agility, athleticism, and work ethic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to athletic performance and skills

    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
    ciation
    -0.76
    Ń·
    -0.74
    Recommend
    -0.70
     Term
    -0.69
    Kids
    -0.68
    ļéĨĴ
    -0.68
    ģĸ
    -0.66
    ĨĴ
    -0.66
    EMS
    -0.65
     Schools
    -0.65
    POSITIVE LOGITS
     charisma
    1.13
     physique
    0.97
     agility
    0.93
    istry
    0.93
     knack
    0.91
     hust
    0.82
     athleticism
    0.81
     deft
    0.81
     athlet
    0.81
     impecc
    0.80
    Activations Density 0.290%

    No Known Activations