© 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. 2-RES-JB
    11. 5305
    Prev
    Next
    INDEX
    Explanations

    references to the word "Upper"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of materials or substances, particularly those ending in "pper"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.79
    è¯
    -0.74
    é¾
    -0.73
     Attribution
    -0.72
     Fundamental
    -0.70
    ģĸ
    -0.66
    åĮ
    -0.66
    DEF
    -0.64
    æĢ
    -0.62
    ALE
    -0.62
    POSITIVE LOGITS
    pper
    1.21
    mint
    1.07
    ppers
    1.05
    iffe
    0.98
    idon
    0.90
    idge
    0.87
    ipher
    0.83
    ipop
    0.81
    ixel
    0.80
    rison
    0.76
    Activations Density 0.013%

    No Known Activations