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. 20657
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures named "Muammar" with differing activations suggesting a focus on specific instances or elements related to the individual throughout the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Muammar."

    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
    代
    -0.90
     Peb
    -0.71
    OME
    -0.69
    EMS
    -0.69
    CAST
    -0.67
     Dispatch
    -0.66
     Dangerous
    -0.65
    peak
    -0.65
     pans
    -0.64
    arantine
    -0.63
    POSITIVE LOGITS
    riages
    1.07
    quez
    0.88
    iously
    0.87
    ques
    0.85
    anth
    0.81
    zynski
    0.79
    iam
    0.78
    rying
    0.76
    quet
    0.76
    ital
    0.75
    Activations Density 0.009%

    No Known Activations