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. 14260
    Prev
    Next
    INDEX
    Explanations

    pronouns 'who' referring to a group of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "who," indicating a focus on individuals or groups being referenced

    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
     Anything
    -0.75
     Anyway
    -0.73
     Delicious
    -0.69
    Rest
    -0.69
     Bound
    -0.69
    ³³³³
    -0.69
    BACK
    -0.64
    Poké
    -0.62
     Basics
    -0.62
     Recovery
    -0.62
    POSITIVE LOGITS
    oping
    1.12
    oped
    1.01
    soever
    0.99
     preceded
    0.97
     specialize
    0.96
     migrated
    0.93
    ppers
    0.90
    ever
    0.89
     resided
    0.89
     participated
    0.87
    Activations Density 0.136%

    No Known Activations