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. 12364
    Prev
    Next
    INDEX
    Explanations

    phrases related to rumors, news, and speculation

    oai_token-act-pair · gpt-3.5-turbo

    negative sentiments regarding ongoing situations or controversies

    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
     (=
    -0.70
    igraph
    -0.67
    )"
    -0.65
    )",
    -0.61
     orally
    -0.59
    ujah
    -0.59
    eva
    -0.57
    heid
    -0.57
    âĢIJ
    -0.56
    ruction
    -0.56
    POSITIVE LOGITS
     nonetheless
    0.79
    etheless
    0.73
     looming
    0.68
     resurg
    0.65
     squarely
    0.63
     downright
    0.62
     precip
    0.62
     headlined
    0.60
     predictably
    0.60
     rattled
    0.60
    Activations Density 1.593%

    No Known Activations