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. 10-RES-JB
    6. 8775
    Prev
    Next
    INDEX
    Explanations

    words indicating a sudden or extreme change in situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving falling or its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shaw
    -0.76
    200000
    -0.75
    iliary
    -0.73
    future
    -0.69
    ilant
    -0.65
    kefeller
    -0.64
    istani
    -0.64
    td
    -0.63
    ilation
    -0.62
    illo
    -0.61
    POSITIVE LOGITS
     bombshell
    1.01
     asleep
    0.95
     inhib
    0.84
     stairs
    0.83
     miser
    0.79
     jaws
    0.78
     precip
    0.75
     bombs
    0.75
     steep
    0.71
     unexpectedly
    0.71
    Activations Density 0.125%

    No Known Activations