© 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. 1-RES-JB
    11. 3650
    Prev
    Next
    INDEX
    Explanations

    descriptive terms for delicate or intricate things

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to fragility and complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hers
    -0.73
    ablishment
    -0.70
    ulhu
    -0.70
    posted
    -0.70
    SPONSORED
    -0.70
    VERTIS
    -0.69
    aze
    -0.69
    arthed
    -0.69
    VERTISEMENT
    -0.69
    GM
    -0.68
    POSITIVE LOGITS
     delicate
    1.44
     sensibilities
    0.97
     delic
    0.89
     balancing
    0.86
     balances
    0.80
     nuance
    0.79
     exqu
    0.79
     balance
    0.78
     adolesc
    0.78
     nuances
    0.77
    Activations Density 0.014%

    No Known Activations