© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9-RES-JB
    11. 10241
    Prev
    Next
    INDEX
    Explanations

    words related to icons or iconic representations

    oai_token-act-pair · gpt-3.5-turbo

    references to "icon" in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Hegel
    -0.69
    EEE
    -0.69
    UGE
    -0.64
     understatement
    -0.62
    THER
    -0.61
     Thoughts
    -0.60
    ingly
    -0.60
    ndum
    -0.60
     Turk
    -0.59
    gaard
    -0.58
    POSITIVE LOGITS
    ocl
    1.64
    ically
    1.22
    nect
    1.20
    icity
    1.13
    ography
    1.07
    ographic
    1.01
    ographically
    0.97
    osite
    0.96
    oc
    0.93
    icons
    0.91
    Activations Density 0.047%

    No Known Activations