© 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. 11-RES-JB
    11. 21899
    Prev
    Next
    INDEX
    Explanations

    phrases related to pointing out or highlighting something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating visual observations or references to seeing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.71
    icum
    -0.71
    uci
    -0.68
    uga
    -0.66
    urses
    -0.65
    etheless
    -0.65
    nih
    -0.64
    uala
    -0.63
    osi
    -0.63
    ont
    -0.63
    POSITIVE LOGITS
     below
    1.22
     above
    0.99
     here
    0.89
     screenshots
    0.86
     clearly
    0.85
     BELOW
    0.85
     HERE
    0.85
     why
    0.83
     screenshot
    0.83
     therein
    0.81
    Activations Density 0.057%

    No Known Activations