© 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. 2-RES-JB
    11. 17604
    Prev
    Next
    INDEX
    Explanations

    icons or symbols within a text

    oai_token-act-pair · gpt-3.5-turbo

    the word "icon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nder
    -0.72
    cible
    -0.71
     Winds
    -0.70
    REAM
    -0.68
    IGH
    -0.67
     Thoughts
    -0.66
    idden
    -0.64
    ndum
    -0.63
    EStreamFrame
    -0.62
    UCK
    -0.62
    POSITIVE LOGITS
    ocl
    1.36
     icon
    1.22
     icons
    1.14
    icons
    0.97
    ographically
    0.91
    icon
    0.90
    ically
    0.90
    nect
    0.87
     Icon
    0.87
    igl
    0.86
    Activations Density 0.007%

    No Known Activations