© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 941
    Prev
    Next
    INDEX
    Explanations

    questions or inquiries

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or questions about knowledge and understanding

    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
    ItemTracker
    -0.96
    phrine
    -0.88
    ĪĴ
    -0.83
    ŃĶ
    -0.82
    amic
    -0.72
    ©¶æ¥µ
    -0.71
     entreprene
    -0.69
    orie
    -0.69
    ©¶æ
    -0.66
    aution
    -0.65
    POSITIVE LOGITS
    ledge
    1.04
     how
    0.90
    lege
    0.85
    ariat
    0.84
     HOW
    0.80
    igan
    0.75
    rounder
    0.75
     why
    0.74
     WHY
    0.74
    ledged
    0.74
    Activations Density 0.043%

    No Known Activations