© 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. 10418
    Prev
    Next
    INDEX
    Explanations

    mentions of a group or collection of items to be processed together

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of items or collections

    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
    ruption
    -0.72
     Episcopal
    -0.71
     Commissioners
    -0.68
    mington
    -0.67
    iasis
    -0.66
     poles
    -0.63
    thy
    -0.61
    acts
    -0.61
    plex
    -0.60
    aleigh
    -0.58
    POSITIVE LOGITS
     batches
    1.14
     batch
    1.09
    mates
    1.00
    batch
    0.87
    fuck
    0.80
    Dispatch
    0.77
    mate
    0.76
    olean
    0.76
    bugs
    0.75
    Iterator
    0.72
    Activations Density 0.006%

    No Known Activations