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. 14282
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to prevalence or pervasiveness

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the prevalence or commonality of concepts or phenomena

    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
     halves
    -0.74
     RELEASE
    -0.73
     Saving
    -0.71
    Edited
    -0.67
     Nanto
    -0.66
     Submission
    -0.65
     increments
    -0.65
     resc
    -0.64
    bro
    -0.64
     Rescue
    -0.64
    POSITIVE LOGITS
     prevalent
    2.70
     pervasive
    2.66
     rampant
    2.58
     ubiquitous
    2.27
     endemic
    2.00
     commonplace
    1.89
     widespread
    1.66
     rife
    1.65
     ubiqu
    1.57
     omnip
    1.53
    Activations Density 0.034%

    No Known Activations