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. 9792
    Prev
    Next
    INDEX
    Explanations

    mentions of garbage or related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to waste management and refuse

    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
    hip
    -0.90
    saf
    -0.83
    nen
    -0.83
    lis
    -0.78
    ffield
    -0.77
    ning
    -0.75
    akening
    -0.75
    imble
    -0.73
    farious
    -0.72
    itude
    -0.71
    POSITIVE LOGITS
     dumps
    1.00
     disposal
    0.95
     garbage
    0.90
     bags
    0.86
     inciner
    0.82
     collection
    0.81
     cans
    0.81
     dump
    0.80
    bags
    0.80
     collector
    0.78
    Activations Density 0.017%

    No Known Activations