© 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. 10-RES-JB
    6. 13719
    Prev
    Next
    INDEX
    Explanations

    proper names and titles, particularly focusing on variations of the name "Andrei"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly in the context of film and sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arah
    -1.05
    ascript
    -1.01
    ecause
    -0.88
    agra
    -0.86
    vana
    -0.84
    taboola
    -0.83
    flix
    -0.82
    grass
    -0.81
    erb
    -0.81
    earchers
    -0.81
    POSITIVE LOGITS
     Ber
    0.91
     Kl
    0.89
     Kir
    0.88
     Vor
    0.87
     Eisen
    0.86
     Ges
    0.85
     Stan
    0.85
     Engels
    0.85
     Kov
    0.84
     Berger
    0.84
    Activations Density 0.092%

    No Known Activations