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. 6-RES-JB
    6. 8139
    Prev
    Next
    INDEX
    Explanations

    combinations of words related to objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itially
    -0.70
    press
    -0.67
     alone
    -0.64
    iance
    -0.62
    stem
    -0.61
    orah
    -0.61
    pressure
    -0.61
    liction
    -0.61
    fighter
    -0.60
    BUG
    -0.59
    POSITIVE LOGITS
     regard
    1.06
     regards
    1.05
    drawn
    1.04
    stood
    1.02
     impunity
    1.01
    draw
    0.85
     respect
    0.78
    trl
    0.70
     dignity
    0.69
    ĪĴ
    0.68
    Activations Density 0.130%

    No Known Activations