© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 24067
    Prev
    Next
    INDEX
    Explanations

    descriptive texts indicating information or details about a certain topic

    oai_token-act-pair · gpt-3.5-turbo

    sections labeled as "Description" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aded
    -0.74
    zig
    -0.74
    lio
    -0.73
     gust
    -0.73
    lling
    -0.69
     emot
    -0.69
     barn
    -0.68
    oppy
    -0.67
     underest
    -0.67
     rubbish
    -0.67
    POSITIVE LOGITS
    Description
    1.23
     Description
    0.93
     Definition
    0.92
    Features
    0.91
     Details
    0.90
     Features
    0.90
     Specifications
    0.89
    isine
    0.89
     Languages
    0.87
     Provides
    0.84
    Activations Density 0.029%

    No Known Activations