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. 24219
    Prev
    Next
    INDEX
    Explanations

    personal pronouns in second person

    oai_token-act-pair · gpt-3.5-turbo

    the word "you," indicating a focus on direct address or engagement with the reader

    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
    iday
    -0.67
    ipal
    -0.64
     hers
    -0.63
     Hook
    -0.61
    kamp
    -0.61
     Chap
    -0.60
     Hyde
    -0.59
    hover
    -0.59
    votes
    -0.58
    official
    -0.58
    POSITIVE LOGITS
     guys
    1.32
    're
    1.30
    've
    1.09
    tub
    1.01
     guessed
    0.90
    'll
    0.86
     gotta
    0.86
     know
    0.85
     yourselves
    0.84
    ngth
    0.82
    Activations Density 0.221%

    No Known Activations