© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6827
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Ada" with different intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ada"

    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
     advisers
    -0.67
    comings
    -0.65
    comes
    -0.65
     clipboard
    -0.65
     advisors
    -0.65
    giving
    -0.64
     backwards
    -0.63
    steps
    -0.62
     backward
    -0.62
     advantages
    -0.61
    POSITIVE LOGITS
    ada
    1.24
    quez
    0.86
    illac
    0.85
    ption
    0.84
    aii
    0.79
    achi
    0.78
    ismo
    0.77
    aeda
    0.76
    ibur
    0.75
    asa
    0.75
    Activations Density 0.009%

    No Known Activations