© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6476
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific brand or product, specifically "aker"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "aker."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bordering
    -0.74
     traffic
    -0.69
     esc
    -0.65
     butterflies
    -0.65
     Ples
    -0.62
     grandchildren
    -0.62
     ten
    -0.62
     childhood
    -0.61
     Comic
    -0.61
     Lep
    -0.60
    POSITIVE LOGITS
    aker
    4.59
    akers
    3.20
    aking
    1.82
    aked
    1.56
    aks
    1.45
    akery
    1.35
    aken
    1.30
    akable
    1.30
    ake
    1.30
    arer
    1.30
    Activations Density 0.011%

    No Known Activations