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. 1672
    Prev
    Next
    INDEX
    Explanations

    mentions of the Department of Energy (DE)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation "DE" 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
    ocene
    -0.88
    imity
    -0.81
    olulu
    -0.80
     BaseType
    -0.78
    toggle
    -0.77
    oulos
    -0.77
    ãĤ¤ãĥĪ
    -0.75
    andise
    -0.73
    ãĥĥãĤ¯
    -0.72
     è£ıè¦ļéĨĴ
    -0.72
    POSITIVE LOGITS
    FAULT
    1.21
    VICE
    1.19
    FIN
    1.12
    POS
    1.03
    FINE
    0.95
    VEL
    0.94
    PUT
    0.90
    ATH
    0.87
    leted
    0.86
    PORT
    0.85
    Activations Density 0.012%

    No Known Activations