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. 3-RES-JB
    6. 21615
    Prev
    Next
    INDEX
    Explanations

    metaphors used in text

    oai_token-act-pair · gpt-3.5-turbo

    references to metaphors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierra
    -0.77
    eded
    -0.74
    emetery
    -0.68
    oway
    -0.65
    packing
    -0.65
    ailable
    -0.61
     Citiz
    -0.61
    WHERE
    -0.60
    astered
    -0.60
    rake
    -0.60
    POSITIVE LOGITS
     metaphor
    0.93
     metaphors
    0.89
    ically
    0.76
    aph
    0.70
     drowning
    0.68
     analogy
    0.67
     drown
    0.67
    gdala
    0.66
     underpin
    0.65
    hemer
    0.65
    Activations Density 0.010%

    No Known Activations