© 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. 11-RES-JB
    6. 1775
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to Korean politics

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their titles or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stream
    -0.74
     Rossi
    -0.72
     Receiver
    -0.67
     Codex
    -0.65
     AVG
    -0.64
     REAL
    -0.63
     Odyssey
    -0.63
     Levant
    -0.62
     blender
    -0.62
     Pengu
    -0.62
    POSITIVE LOGITS
    sung
    1.27
    ahn
    1.16
    hung
    1.11
    Hy
    1.10
    Je
    1.09
    moon
    1.03
    jin
    1.02
    Shin
    1.01
    su
    1.01
    Wan
    1.01
    Activations Density 0.026%

    No Known Activations