© 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. 2-RES-JB
    11. 9276
    Prev
    Next
    INDEX
    Explanations

    metadata-related terms or concepts in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uran
    -0.74
    ndra
    -0.74
    arm
    -0.73
    ggle
    -0.71
    armac
    -0.71
    atan
    -0.71
    atism
    -0.70
    ghai
    -0.70
    awar
    -0.70
    osi
    -0.69
    POSITIVE LOGITS
     metadata
    1.16
    adata
    1.07
    metadata
    0.94
     databases
    0.73
     datasets
    0.73
     tagging
    0.72
     lookup
    0.71
     metab
    0.71
    ãĤ´
    0.70
     data
    0.70
    Activations Density 0.008%

    No Known Activations