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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17098
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to timeframes and specific events

    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
     vulner
    -0.54
     theirs
    -0.53
    )."
    -0.48
    ]."
    -0.46
     ..."
    -0.46
     respectively
    -0.46
    ".[
    -0.45
    .</
    -0.44
    76561
    -0.42
    transform
    -0.42
    POSITIVE LOGITS
    undrum
    0.55
    eport
    0.55
     partName
    0.52
    ibliography
    0.52
    ĻĤ
    0.51
    odcast
    0.50
    endum
    0.49
    emonium
    0.49
    zsche
    0.48
     aback
    0.48
    Activations Density 7.228%

    No Known Activations