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. 10783
    Prev
    Next
    INDEX
    Explanations

    the word "consistently" followed by a word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "consistently" and its variants highlighting ongoing behavior or patterns

    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
    iku
    -0.69
    ubes
    -0.62
    minus
    -0.62
     burial
    -0.61
    body
    -0.60
     ANG
    -0.59
    ous
    -0.58
    ussion
    -0.57
    private
    -0.57
     Translation
    -0.57
    POSITIVE LOGITS
     consistently
    3.27
     reliably
    2.20
     routinely
    1.80
     consistent
    1.79
     regularly
    1.76
     continually
    1.69
     uniformly
    1.66
     repeatedly
    1.64
     continuously
    1.64
     systematically
    1.55
    Activations Density 0.020%

    No Known Activations