© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 18474
    Prev
    Next
    INDEX
    Explanations

    instances of the word "metadata"

    oai_token-act-pair · gpt-3.5-turbo

    references to metadata

    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
    awar
    -0.89
    ndra
    -0.83
    zee
    -0.72
    atan
    -0.71
    bye
    -0.70
    boat
    -0.70
    ggle
    -0.70
    orea
    -0.68
    atism
    -0.67
    swick
    -0.67
    POSITIVE LOGITS
    adata
    0.97
     metadata
    0.82
    metadata
    0.81
     retrieval
    0.78
    ãĤ´
    0.78
     extracted
    0.73
     data
    0.69
     databases
    0.68
     trove
    0.68
     buckets
    0.67
    Activations Density 0.026%

    No Known Activations