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. 3-RES-JB
    6. 10943
    Prev
    Next
    INDEX
    Explanations

    references to natural environments, especially jungles, and related terms such as camouflage and bamboo

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "jungle" and related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    viation
    -0.92
     Mellon
    -0.75
    idel
    -0.74
    igating
    -0.74
    idem
    -0.73
    Asset
    -0.72
    aton
    -0.71
    ghai
    -0.70
    edy
    -0.70
    ÑĮ
    -0.70
    POSITIVE LOGITS
     jungle
    1.08
     Jungle
    1.02
    ungle
    0.91
     jung
    0.86
     Warfare
    0.82
     lion
    0.81
     Hatt
    0.79
     camps
    0.75
     Jade
    0.70
     Aj
    0.70
    Activations Density 0.006%

    No Known Activations