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. 18289
    Prev
    Next
    INDEX
    Explanations

    phrases related to ensuring a specific action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the importance of ensuring safety and security

    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
     Yao
    -0.73
    HF
    -0.70
    Rated
    -0.67
    script
    -0.64
    PsyNetMessage
    -0.63
     Zig
    -0.63
    ufact
    -0.62
    gression
    -0.62
    gdala
    -0.61
    robe
    -0.61
    POSITIVE LOGITS
    ariat
    0.74
    ties
    0.67
     fertil
    0.66
     customers
    0.64
     ensure
    0.62
     liv
    0.59
     deliveries
    0.59
    uth
    0.59
     pol
    0.58
     dent
    0.58
    Activations Density 0.023%

    No Known Activations