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. 12574
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'hemp'

    oai_token-act-pair · gpt-3.5-turbo

    references to hemp and related topics

    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
    ysis
    -0.93
    oice
    -0.71
     Catalog
    -0.68
     Debor
    -0.66
     downgrade
    -0.66
     Nile
    -0.65
    ror
    -0.64
     Barcl
    -0.64
     Viper
    -0.62
     reluct
    -0.61
    POSITIVE LOGITS
    stead
    1.20
     Hemp
    1.03
     hemp
    0.98
    seed
    0.86
     cultivation
    0.82
     farming
    0.81
    cott
    0.78
     Farming
    0.76
    crete
    0.76
    leaf
    0.75
    Activations Density 0.013%

    No Known Activations