© 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. 0-RES-JB
    6. 5408
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and technology applications

    oai_token-act-pair · gpt-3.5-turbo

    references to software applications or related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghazi
    -0.69
    flame
    -0.67
    ̶
    -0.67
    staff
    -0.62
     Palest
    -0.61
    ravings
    -0.61
     moderates
    -0.61
    oiler
    -0.61
    cephal
    -0.60
    Ryan
    -0.60
    POSITIVE LOGITS
     application
    3.70
     applications
    2.79
     Application
    2.74
    application
    2.74
    Application
    2.53
     Applications
    2.23
     applic
    2.02
     APPLIC
    1.93
    Applications
    1.92
     applicant
    1.81
    Activations Density 0.012%

    No Known Activations