© 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. 4-RES-JB
    11. 695
    Prev
    Next
    INDEX
    Explanations

    mentions of important events or developments

    oai_token-act-pair · gpt-3.5-turbo

    the term "major" in various contexts related to significance or importance

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

    No Comments

    Negative Logits
     Machina
    -0.78
    metry
    -0.74
    mates
    -0.72
    mons
    -0.70
    tein
    -0.70
    env
    -0.69
    mate
    -0.68
     Leone
    -0.67
     Vaugh
    -0.66
     Zombies
    -0.64
    POSITIVE LOGITS
    itarian
    0.96
     depressive
    0.93
     contributor
    0.82
     arteries
    0.80
    itized
    0.78
     understatement
    0.76
     overhaul
    0.74
     artery
    0.72
     contributors
    0.72
    stay
    0.71
    Activations Density 0.026%

    No Known Activations