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. 21629
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructing or providing guidance on various topics or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "How to."

    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
    lights
    -0.82
    enance
    -0.78
     Coff
    -0.78
     Appears
    -0.73
    court
    -0.67
     Nightmares
    -0.66
     Boone
    -0.65
    mails
    -0.64
    urance
    -0.64
    comments
    -0.63
    POSITIVE LOGITS
     navigate
    1.24
     prepare
    1.11
     evade
    1.11
     proceed
    1.11
     achieve
    1.11
     avoid
    1.09
     overcome
    1.08
     circumvent
    1.08
     organize
    1.07
     manage
    1.07
    Activations Density 0.078%

    No Known Activations