© 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. 11-RES-JB
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    devices and technologies related to "smart" features

    oai_token-act-pair · gpt-3.5-turbo

    references to smart technology and connected devices

    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
     McDonnell
    -0.76
    agall
    -0.70
     OPEC
    -0.68
    ̶
    -0.66
    hedral
    -0.65
     Granger
    -0.65
     Welch
    -0.64
    ANA
    -0.63
     behold
    -0.61
     Bundy
    -0.61
    POSITIVE LOGITS
    watch
    1.31
    phone
    1.31
    phones
    1.26
    Things
    0.98
    paren
    0.92
    bomb
    0.90
     phones
    0.90
    Glass
    0.89
    shield
    0.89
    gart
    0.87
    Activations Density 0.037%

    No Known Activations