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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8180
    Prev
    Next
    INDEX
    Explanations

    references to bananas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of the word "banana"

    oai_token-act-pair · gpt-3.5-turbo
    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
    Ö¼
    -0.83
    enegger
    -0.82
    yll
    -0.82
     Cosponsors
    -0.78
    pter
    -0.75
    arnaev
    -0.73
    ROR
    -0.71
    performance
    -0.70
    tml
    -0.70
    sch
    -0.69
    POSITIVE LOGITS
     banana
    1.11
     bananas
    1.10
     peel
    0.94
     pancakes
    0.87
     pudding
    0.87
     toast
    0.86
     carrot
    0.82
     fruit
    0.81
     Banana
    0.80
    fruit
    0.80
    Activations Density 0.008%

    No Known Activations