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. 8-RES-JB
    6. 15985
    Prev
    Next
    INDEX
    Explanations

    phrases related to writing books or articles about various topics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "about" in relation to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terness
    -0.70
    stretched
    -0.67
    quez
    -0.66
    nai
    -0.66
     Sabha
    -0.65
    ©¶æ¥µ
    -0.64
     briefed
    -0.64
    nas
    -0.63
    hes
    -0.63
    bered
    -0.62
    POSITIVE LOGITS
     overcoming
    0.76
     how
    0.74
     topics
    0.72
     why
    0.68
     reforming
    0.67
    =#
    0.64
     HERO
    0.61
     UFOs
    0.61
     piracy
    0.60
    aturday
    0.60
    Activations Density 0.169%

    No Known Activations