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. 6090
    Prev
    Next
    INDEX
    Explanations

    phrases that start with "For starters," or variations thereof

    oai_token-act-pair · gpt-3.5-turbo

    the word "starters" and its variations relating to introductory concepts or items

    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
    ur
    -0.70
    ud
    -0.65
    agh
    -0.65
    odd
    -0.65
    or
    -0.59
    arger
    -0.59
    may
    -0.59
    aminer
    -0.59
    igmat
    -0.58
    qa
    -0.58
    POSITIVE LOGITS
     starters
    4.08
     starter
    1.76
     backups
    1.17
     regulars
    1.16
     pitchers
    1.12
     beginners
    1.11
     Starter
    1.10
     rookies
    1.09
     starting
    1.03
     staples
    1.02
    Activations Density 0.010%

    No Known Activations