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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14246
    Prev
    Next
    INDEX
    Explanations

    places or things related to "Garden" or "Gardener"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of "Gard" or similar variations, indicating a focus on a specific entity or name throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.89
    pson
    -0.80
    rities
    -0.72
    opian
    -0.71
    phrine
    -0.69
    BIP
    -0.67
    igslist
    -0.67
    izable
    -0.67
    uates
    -0.64
    olutions
    -0.62
    POSITIVE LOGITS
    llan
    1.00
    ener
    0.89
    gard
    0.89
    ening
    0.86
    endale
    0.84
     Gard
    0.82
     Mechdragon
    0.82
    are
    0.80
    ith
    0.80
    inia
    0.77
    Activations Density 0.019%

    No Known Activations