© 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. 1-RES-JB
    11. 14388
    Prev
    Next
    INDEX
    Explanations

    phrases related to document processing, specifically focusing on data backup and restoration

    oai_token-act-pair · gpt-3.5-turbo

    references to data backup or restoration processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quart
    -0.87
    erella
    -0.81
    ãĥĺ
    -0.76
    zos
    -0.75
    oliath
    -0.75
    inav
    -0.73
    cox
    -0.73
    vantage
    -0.70
    nos
    -0.70
    ischer
    -0.69
    POSITIVE LOGITS
     courtyard
    0.64
     wound
    0.63
     forgiveness
    0.61
     ÙĪ
    0.61
     Justice
    0.59
    enei
    0.58
     intersections
    0.57
    pace
    0.57
    ixties
    0.57
     cosmos
    0.56
    Activations Density 0.000%

    No Known Activations