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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 16997
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ana" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ana" in various forms

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

    No Comments

    Negative Logits
    enegger
    -0.86
    tyard
    -0.84
    ²¾
    -0.82
    neys
    -0.82
    paio
    -0.80
    kefeller
    -0.78
    going
    -0.75
    GoldMagikarp
    -0.74
    ties
    -0.74
    tle
    -0.74
    POSITIVE LOGITS
    uthor
    1.08
    eus
    0.99
    esthesia
    0.96
    issance
    0.89
     Scotia
    0.83
    qua
    0.82
     Lima
    0.82
     Grande
    0.81
    utical
    0.79
     Rica
    0.77
    Activations Density 0.013%

    No Known Activations