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. 3-RES-JB
    6. 1681
    Prev
    Next
    INDEX
    Explanations

    terms related to smuggling activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to smuggling activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phasis
    -0.86
    irements
    -0.79
    soType
    -0.76
    abeth
    -0.73
    rises
    -0.72
    isites
    -0.68
    @#&
    -0.67
    MN
    -0.67
    ĪĴ
    -0.66
    awks
    -0.66
    POSITIVE LOGITS
     smuggling
    1.23
     smuggled
    1.19
     smugg
    1.14
     smugglers
    1.03
     trafficking
    0.90
     traffickers
    0.85
    glers
    0.79
     infiltr
    0.77
    oad
    0.75
     transporting
    0.74
    Activations Density 0.011%

    No Known Activations