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. 22605
    Prev
    Next
    INDEX
    Explanations

    words related to solving or addressing issues

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to correction or fixing problems

    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
    cade
    -0.65
    ortment
    -0.64
     headlined
    -0.63
     accompanied
    -0.63
    ever
    -0.63
     placed
    -0.61
     invitation
    -0.61
    luster
    -0.60
    umer
    -0.60
    pmwiki
    -0.60
    POSITIVE LOGITS
    balance
    0.79
    iencies
    0.75
     grievances
    0.72
    ysis
    0.72
    igate
    0.71
    ilitating
    0.71
     them
    0.69
    uate
    0.67
    ulate
    0.67
     their
    0.65
    Activations Density 0.118%

    No Known Activations