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. 18815
    Prev
    Next
    INDEX
    Explanations

    instances where something undergoes a transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "become" in various contexts

    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
    inarily
    -0.75
    inately
    -0.75
    osite
    -0.69
    ramid
    -0.69
    oning
    -0.68
    orney
    -0.68
    alian
    -0.67
    atching
    -0.67
    otropic
    -0.66
    bell
    -0.64
    POSITIVE LOGITS
     accustomed
    0.96
     entangled
    0.89
     extinct
    0.84
     embroiled
    0.79
    nces
    0.79
     disillusion
    0.78
     undone
    0.78
     acquainted
    0.77
     obsolete
    0.76
     unman
    0.76
    Activations Density 0.047%

    No Known Activations