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. 9-RES-JB
    6. 4416
    Prev
    Next
    INDEX
    Explanations

    terms related to the effectiveness or impact of various actions or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "effect" and its various applications or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pigeon
    -0.83
     Timber
    -0.68
    croft
    -0.67
     Methodist
    -0.66
    mbuds
    -0.66
     Alto
    -0.64
    dig
    -0.64
     Dud
    -0.64
     Skies
    -0.61
    mint
    -0.61
    POSITIVE LOGITS
    iveness
    1.43
    ual
    1.28
    uated
    1.22
    uating
    1.16
    ively
    1.15
    uation
    1.08
    ually
    1.08
    uate
    1.07
    uates
    1.00
    uality
    0.98
    Activations Density 0.061%

    No Known Activations