© 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. 10330
    Prev
    Next
    INDEX
    Explanations

    the word "voila" with different variations in spelling and formatting

    oai_token-act-pair · gpt-3.5-turbo

    the word "voice" and related terms

    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
    arya
    -0.74
    itect
    -0.73
     wills
    -0.69
     throats
    -0.68
     è£ıè¦ļéĨĴ
    -0.68
     needles
    -0.66
     ACTIONS
    -0.65
    rylic
    -0.64
     Principles
    -0.63
    20439
    -0.63
    POSITIVE LOGITS
     vo
    1.31
    iture
    0.97
     prest
    0.87
    hua
    0.85
    milo
    0.80
    iage
    0.78
    inion
    0.78
    loop
    0.77
    orld
    0.74
    ouver
    0.72
    Activations Density 0.021%

    No Known Activations