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. 0-RES-JB
    6. 10715
    Prev
    Next
    INDEX
    Explanations

    instances where something or someone is in the process of changing or evolving to a new state or position

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "becoming."

    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
    ï¸ı
    -0.69
     largeDownload
    -0.66
    #$
    -0.65
    MD
    -0.61
    rote
    -0.61
    place
    -0.60
    gow
    -0.60
    =-=-=-=-
    -0.59
     IMAGES
    -0.58
     Wait
    -0.58
    POSITIVE LOGITS
     becoming
    3.23
     gaining
    1.72
     become
    1.63
     joining
    1.49
    bec
    1.47
     being
    1.47
     acquiring
    1.43
     adopting
    1.38
     forming
    1.38
     succeeding
    1.37
    Activations Density 0.017%

    No Known Activations