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. 3806
    Prev
    Next
    INDEX
    Explanations

    metaphors

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "metaphor" and related terms

    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
    ierra
    -0.76
    eded
    -0.73
    reditary
    -0.67
    bred
    -0.65
    cho
    -0.64
    selection
    -0.63
    issue
    -0.61
    efficients
    -0.61
     Pon
    -0.60
    FI
    -0.60
    POSITIVE LOGITS
     metaphor
    0.95
    ically
    0.87
     metaphors
    0.81
    izon
    0.70
    gdala
    0.69
     GOODMAN
    0.68
     drown
    0.68
     analogy
    0.67
     drowning
    0.66
     writ
    0.65
    Activations Density 0.015%

    No Known Activations