© 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. 7-RES-JB
    11. 20743
    Prev
    Next
    INDEX
    Explanations

    technical terms related to machinery or automotive components

    oai_token-act-pair · gpt-3.5-turbo

    descriptors for speed and performance

    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
     Marketplace
    -0.66
     ObamaCare
    -0.61
     cybersecurity
    -0.61
     FBI
    -0.59
    CNN
    -0.58
     Medicaid
    -0.58
     cellphone
    -0.57
     Replay
    -0.56
     Idaho
    -0.56
     Obamacare
    -0.55
    POSITIVE LOGITS
     Whilst
    0.91
     util
    0.88
     whilst
    0.86
     furthermore
    0.83
     moreover
    0.79
     dexter
    0.73
     hitherto
    0.72
     sublime
    0.72
     gazing
    0.71
     envis
    0.70
    Activations Density 1.591%

    No Known Activations