© 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. 17693
    Prev
    Next
    INDEX
    Explanations

    people's names, particularly names like "Ranieri" and "Conan" with varying activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the football coach Claudio Ranieri

    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
    é¾įå¥ij士
    -0.90
    ĨĴ
    -0.85
     butterfly
    -0.74
    quickShipAvailable
    -0.70
    £ı
    -0.69
    shapeshifter
    -0.66
    */(
    -0.64
    URR
    -0.64
     Mississ
    -0.63
     pinpoint
    -0.61
    POSITIVE LOGITS
    interstitial
    0.99
     Ran
    0.97
    ieri
    0.91
    vier
    0.88
    aldo
    0.86
    igans
    0.86
    uled
    0.82
    sei
    0.81
    zan
    0.80
    adium
    0.80
    Activations Density 0.010%

    No Known Activations