© 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. 7-RES-JB
    11. 1517
    Prev
    Next
    INDEX
    Explanations

    verbs related to control, influence, or supremacy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dominance or control over something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    endment
    -0.68
    spir
    -0.66
    dra
    -0.62
    zn
    -0.62
    pt
    -0.62
    ensions
    -0.61
    endi
    -0.61
    ead
    -0.61
     defect
    -0.61
    resso
    -0.61
    POSITIVE LOGITS
     headlines
    0.82
     dominated
    0.74
     overshadowed
    0.72
     dominates
    0.65
    Ń·
    0.64
     charge
    0.63
    quez
    0.62
    pread
    0.62
    ICS
    0.62
    creen
    0.62
    Activations Density 0.037%

    No Known Activations