Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 8069
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "covered"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "covered" and variations of it, along with related terms indicating location or replacement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usable
    -0.77
    asters
    -0.70
    socket
    -0.65
    piece
    -0.64
    parts
    -0.64
    stem
    -0.64
    女
    -0.64
    upon
    -0.61
    pieces
    -0.59
    Wave
    -0.59
    POSITIVE LOGITS
    atchewan
    0.78
     Huckabee
    0.73
    vironment
    0.73
    creen
    0.72
     Direction
    0.72
    enhagen
    0.71
    tenance
    0.71
    =-=-=-=-
    0.71
    krit
    0.71
    allery
    0.70
    Activations Density 0.044%

    No Known Activations