Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5584
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of fruits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fruit

    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
     Weld
    -0.79
     SQ
    -0.67
     #####
    -0.67
     MGM
    -0.66
    iege
    -0.66
     Osw
    -0.65
    Ther
    -0.65
     Lets
    -0.65
    anyon
    -0.64
     Compensation
    -0.64
    POSITIVE LOGITS
     fruit
    3.72
     fruits
    2.96
     Fruit
    2.54
    fruit
    2.49
     berries
    1.78
     grapes
    1.78
     strawberries
    1.65
     mango
    1.61
    ruits
    1.56
     bananas
    1.52
    Activations Density 0.013%

    No Known Activations