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. 7-RES-JB
    6. 10401
    Prev
    Next
    INDEX
    Explanations

    phrases related to forceful actions or impacts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.71
    isted
    -0.69
    juven
    -0.69
    etus
    -0.69
    CTV
    -0.66
    OST
    -0.65
    onomy
    -0.64
     whales
    -0.64
    arily
    -0.64
    IST
    -0.64
    POSITIVE LOGITS
    )=(
    0.70
    drive
    0.69
     waivers
    0.67
    inventoryQuantity
    0.67
    ierre
    0.66
     Weld
    0.64
     Rodrig
    0.64
     Sussex
    0.64
    shaw
    0.62
    ensibly
    0.61
    Activations Density 0.046%

    No Known Activations