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

    Neuronpedia

    APICircuit 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. 2-RES-JB
    6. 19178
    Prev
    Next
    INDEX
    Explanations

    prices or quantities of specific fruits

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the fruit "apple."

    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
    interrupted
    -0.83
    uled
    -0.76
    efeated
    -0.72
    ocumented
    -0.71
    emporary
    -0.67
    citizens
    -0.66
     Tsarnaev
    -0.65
     Gazette
    -0.64
    gettable
    -0.64
     Roose
    -0.64
    POSITIVE LOGITS
     apple
    1.40
     cider
    1.33
     apples
    1.31
    apple
    1.10
    fruit
    1.05
     juice
    1.01
    baum
    0.97
     pie
    0.93
     pies
    0.92
    jack
    0.90
    Activations Density 0.015%

    No Known Activations