Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 263
    Prev
    Next
    INDEX
    Explanations

    phrases related to different varieties of things

    oai_token-act-pair · gpt-3.5-turbo

    mentions of agricultural varieties, particularly in the context of plants and crops

    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
    deen
    -0.70
    duct
    -0.67
    sle
    -0.67
    road
    -0.65
    zie
    -0.65
    venture
    -0.65
    ccording
    -0.64
    ohan
    -0.63
    Sports
    -0.63
    neapolis
    -0.62
    POSITIVE LOGITS
     varieties
    1.03
     strains
    0.86
     hone
    0.78
     bred
    0.74
     blends
    0.74
     thrive
    0.72
     Variety
    0.70
     thri
    0.70
     thereof
    0.70
     crops
    0.69
    Activations Density 0.044%

    No Known Activations