© 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. 0-RES-JB
    11. 5411
    Prev
    Next
    INDEX
    Explanations

    references to bananas

    oai_token-act-pair · gpt-3.5-turbo

    references to bananas and related fruit imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lev
    -0.87
    stre
    -0.86
     Shed
    -0.83
     Lear
    -0.80
    quest
    -0.73
    Tem
    -0.72
    Eng
    -0.71
    Gil
    -0.71
    IRE
    -0.71
     Ward
    -0.70
    POSITIVE LOGITS
     banana
    3.58
     bananas
    3.29
     Banana
    2.73
     mango
    1.92
     pineapple
    1.70
     strawberries
    1.65
     oranges
    1.63
     gorilla
    1.57
     strawberry
    1.52
     peach
    1.42
    Activations Density 0.027%

    No Known Activations