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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 3353
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "just."

    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
     seiz
    -0.76
    undai
    -0.73
     fuse
    -0.73
     necks
    -0.73
    antis
    -0.67
    yip
    -0.67
     destro
    -0.67
    insula
    -0.65
    leneck
    -0.63
    ixel
    -0.63
    POSITIVE LOGITS
    ifiable
    1.32
    ifications
    1.01
    IFIED
    0.96
     kidding
    0.95
     plain
    0.90
    ified
    0.84
    if
    0.83
    itia
    0.76
     gonna
    0.75
    ices
    0.74
    Activations Density 0.048%

    No Known Activations