© 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. 10-RES-JB
    11. 18571
    Prev
    Next
    INDEX
    Explanations

    instances of specific numeric values and their potential implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to sections or paragraphs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighb
    -0.77
     citiz
    -0.77
    aditional
    -0.76
    Þ
    -0.72
     ageing
    -0.70
     nomine
    -0.68
     individuality
    -0.68
     footing
    -0.67
     proport
    -0.67
     newcom
    -0.65
    POSITIVE LOGITS
    ³³³³³³³³
    0.89
    ³³³
    0.89
    ³³³³³³³³³³³³³³³³
    0.87
    ³³
    0.87
    SPONSORED
    0.84
    Sounds
    0.83
    ³³³³
    0.81
    ????????
    0.81
    Ironically
    0.80
    Notice
    0.80
    Activations Density 0.329%

    No Known Activations