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. 4050
    Prev
    Next
    INDEX
    Explanations

    words with the prefix "re-" followed by an action or concept

    oai_token-act-pair · gpt-3.5-turbo

    words related to prefixes denoting a state or condition, especially those starting with "ac" or "en."

    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
     shorth
    -0.80
     Spa
    -0.75
    EVA
    -0.72
     Piper
    -0.69
     Kot
    -0.68
     Christensen
    -0.68
     shaved
    -0.66
     Cot
    -0.66
     Gap
    -0.65
     Shots
    -0.65
    POSITIVE LOGITS
    minent
    1.05
    ertain
    1.03
    ception
    1.03
    mosp
    1.01
    ploy
    1.00
    usterity
    0.98
    istant
    0.97
    terior
    0.97
    emption
    0.96
    velop
    0.95
    Activations Density 0.124%

    No Known Activations