© 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. 7647
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "lemon"

    oai_token-act-pair · gpt-3.5-turbo

    references to lemons and lemon-related concepts

    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
    States
    -0.77
     Pension
    -0.76
    raints
    -0.75
    Desc
    -0.75
    ¥µ
    -0.75
    WER
    -0.75
    ITNESS
    -0.72
     Survivors
    -0.71
    ollow
    -0.70
    legates
    -0.70
    POSITIVE LOGITS
     juice
    1.06
     lemon
    0.99
     bal
    0.89
     peel
    0.88
     fruits
    0.88
     Lemon
    0.86
     squee
    0.84
    ade
    0.84
    fruit
    0.82
     juices
    0.82
    Activations Density 0.007%

    No Known Activations