© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 4581
    Prev
    Next
    INDEX
    Explanations

    proper names or terms likely related to a specific person or place, like "Eckert," "Benson," and "Arn."

    oai_token-act-pair · gpt-3.5-turbo

    proper names or references to individuals, particularly those that are connected to notable achievements or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oleon
    -0.77
    milo
    -0.75
    bered
    -0.71
    mpeg
    -0.70
     Remastered
    -0.70
    ember
    -0.70
     externalToEVAOnly
    -0.69
     Tycoon
    -0.67
     Cavaliers
    -0.65
    DragonMagazine
    -0.65
    POSITIVE LOGITS
    minster
    0.74
    lein
    0.73
    velop
    0.72
    breakers
    0.72
     quo
    0.72
    interstitial
    0.71
    ijk
    0.70
    ansas
    0.70
    hart
    0.69
    abis
    0.69
    Activations Density 0.028%

    No Known Activations