© 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. 17560
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Fle" with different activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Flea" and related variations

    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
    Demand
    -0.70
    LESS
    -0.65
     Hussein
    -0.64
     Mandarin
    -0.61
    quickShipAvailable
    -0.61
    agonist
    -0.61
     Japanese
    -0.60
    ript
    -0.60
     Patriarch
    -0.60
    raint
    -0.60
    POSITIVE LOGITS
    fle
    1.10
     Fle
    0.96
    uve
    0.95
    llo
    0.93
    erie
    0.86
    mington
    0.83
    bes
    0.80
    bats
    0.79
    rets
    0.79
    Fle
    0.79
    Activations Density 0.008%

    No Known Activations