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. 6288
    Prev
    Next
    INDEX
    Explanations

    political entities, individuals, or entities relevant in various fields or contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups and their roles in various contexts

    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
    ategory
    -0.86
    EStreamFrame
    -0.82
    arnaev
    -0.79
     srf
    -0.77
    eanor
    -0.72
    entanyl
    -0.69
    rontal
    -0.69
    raints
    -0.68
    aughtered
    -0.68
     carbohyd
    -0.67
    POSITIVE LOGITS
     deems
    0.97
     lacked
    0.78
     sorely
    0.77
     lacks
    0.76
     might
    0.75
     deem
    0.72
     possesses
    0.67
     excel
    0.67
     wished
    0.67
     ought
    0.66
    Activations Density 0.449%

    No Known Activations