© 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. 0-RES-JB
    11. 9608
    Prev
    Next
    INDEX
    Explanations

    mentions of lines or line-related concepts

    oai_token-act-pair · gpt-3.5-turbo

    words related to financial or economic values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stabilization
    -0.62
     hold
    -0.61
     premature
    -0.61
     mission
    -0.58
     sponsorship
    -0.58
     favor
    -0.57
     balloon
    -0.57
     moot
    -0.57
     circulated
    -0.56
     sponsored
    -0.56
    POSITIVE LOGITS
    ines
    4.55
    ine
    2.50
    INE
    2.31
    ined
    2.17
    iners
    2.00
    ining
    1.93
    iner
    1.82
    inery
    1.54
    inas
    1.53
    inem
    1.52
    Activations Density 0.012%

    No Known Activations