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. 1-RES-JB
    6. 13714
    Prev
    Next
    INDEX
    Explanations

    metaphors or symbolic language

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "metaphor" and variations of it in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierra
    -0.71
    mails
    -0.66
    eded
    -0.64
     Pon
    -0.64
    cho
    -0.64
    vals
    -0.64
    bred
    -0.62
    packing
    -0.62
     Parenthood
    -0.61
    VD
    -0.61
    POSITIVE LOGITS
     metaphor
    1.13
     metaphors
    0.87
     analogy
    0.80
    gdala
    0.79
     GOODMAN
    0.77
    ically
    0.76
     drowning
    0.73
    ufact
    0.70
     wink
    0.67
    izon
    0.67
    Activations Density 0.007%

    No Known Activations