Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11657
    Prev
    Next
    INDEX
    Explanations

    names and variations of the name "Matthew"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly the name "Mathew" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    govtrack
    -0.77
     separat
    -0.74
    Downloadha
    -0.69
     reinforcement
    -0.68
    gency
    -0.67
     fixation
    -0.67
     recharge
    -0.66
     plun
    -0.65
     sovere
    -0.65
     adversaries
    -0.65
    POSITIVE LOGITS
    orld
    0.99
    hew
    0.96
    hews
    0.95
    adow
    0.87
    bean
    0.85
    enegger
    0.84
    anan
    0.83
    toe
    0.83
    afer
    0.81
    orah
    0.81
    Activations Density 0.023%

    No Known Activations