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. 8-RES-JB
    6. 3659
    Prev
    Next
    INDEX
    Explanations

    statements related to societal, economic, and environmental impacts

    oai_token-act-pair · gpt-3.5-turbo

    commonly used conjunctions and pauses in sentences

    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
    scription
    -0.68
    ety
    -0.66
    ãĤ¦ãĤ¹
    -0.65
    lord
    -0.65
    chanted
    -0.64
    iatus
    -0.62
    emonium
    -0.60
    xit
    -0.60
    âķIJ
    -0.59
    REDACTED
    -0.58
    POSITIVE LOGITS
     improve
    1.08
     enhance
    1.05
     thereby
    1.03
     reduce
    1.03
     simplify
    0.99
     eliminate
    0.99
     promote
    0.97
     including
    0.97
     automate
    0.96
     especially
    0.96
    Activations Density 0.385%

    No Known Activations