© 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. 20780
    Prev
    Next
    INDEX
    Explanations

    words related to comparisons between different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals, communities, and general categories related to societal contributions

    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
    Accessory
    -0.71
     Enough
    -0.67
     IPM
    -0.65
     Appropri
    -0.63
    iasis
    -0.63
    Quantity
    -0.62
     Warranty
    -0.62
    irst
    -0.60
     Encyclopedia
    -0.60
    lua
    -0.60
    POSITIVE LOGITS
     besides
    0.98
    worldly
    0.89
     alike
    0.77
    heastern
    0.72
    hops
    0.69
     describ
    0.69
     affili
    0.69
    evin
    0.68
     influences
    0.67
     includ
    0.67
    Activations Density 0.440%

    No Known Activations