© 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. 4-RES-JB
    11. 22359
    Prev
    Next
    INDEX
    Explanations

    words related to dogs and dog-related contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to dogs, particularly in various contexts

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

    No Comments

    Negative Logits
    theless
    -0.65
     cryst
    -0.65
    noon
    -0.64
    aves
    -0.63
     compr
    -0.62
    hur
    -0.62
    owment
    -0.61
     increment
    -0.61
    idential
    -0.59
    aren
    -0.56
    POSITIVE LOGITS
    gers
    1.32
    glers
    1.04
    mire
    1.01
    ging
    0.97
    ger
    0.96
    gy
    0.95
    é»Ĵ
    0.91
    ãĤĮ
    0.91
    ga
    0.90
    ogging
    0.89
    Activations Density 0.025%

    No Known Activations