© 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. 5206
    Prev
    Next
    INDEX
    Explanations

    phrases related to TV shows, channels, and media platforms

    oai_token-act-pair · gpt-3.5-turbo
    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
     elector
    -0.85
    eric
    -0.72
    eting
    -0.72
    eur
    -0.71
    hes
    -0.71
    rians
    -0.70
     cant
    -0.69
     tert
    -0.68
    haar
    -0.67
    aniel
    -0.67
    POSITIVE LOGITS
    Bang
    1.03
    Zone
    1.02
     Squad
    1.00
    Bone
    0.98
    Pop
    0.96
    Kid
    0.96
     Monkey
    0.96
    Girls
    0.96
     Daddy
    0.95
     Factory
    0.94
    Activations Density 0.165%

    No Known Activations