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. 10570
    Prev
    Next
    INDEX
    Explanations

    words related to time, effort, and resources being spent or invested

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial expenditure and investment

    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
    ĪĴ
    -0.68
    jer
    -0.64
     relent
    -0.60
     legality
    -0.58
    eda
    -0.58
     truce
    -0.57
     slogans
    -0.56
     prevail
    -0.55
    ezvous
    -0.54
    Sit
    -0.54
    POSITIVE LOGITS
     expended
    0.99
     devoted
    0.95
     spent
    0.91
     invested
    0.91
     wasted
    0.88
    illion
    0.86
     dedicate
    0.81
     (£
    0.78
     expenditures
    0.78
    pees
    0.77
    Activations Density 0.808%

    No Known Activations