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. 6755
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of maximizing potential or benefit

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "best possible" or "greatest possible" outcomes

    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
    cius
    -0.86
    wan
    -0.74
    yer
    -0.74
    masters
    -0.74
    wa
    -0.73
    gar
    -0.72
    ling
    -0.72
    gy
    -0.70
    irs
    -0.69
    lt
    -0.69
    POSITIVE LOGITS
    Versions
    0.83
     practicable
    0.74
     selves
    0.71
     versions
    0.71
    arial
    0.70
     outcomes
    0.70
     toile
    0.69
     embodiment
    0.69
     embodiments
    0.67
     worlds
    0.67
    Activations Density 0.038%

    No Known Activations