© 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. 1699
    Prev
    Next
    INDEX
    Explanations

    phrases related to development teams

    oai_token-act-pair · gpt-3.5-turbo

    mentions of development teams

    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
    ulia
    -0.71
    ãģĦ
    -0.68
    ihu
    -0.68
    icted
    -0.66
    other
    -0.65
     Giuliani
    -0.65
    gyn
    -0.64
    onna
    -0.64
    otropic
    -0.64
    aukee
    -0.63
    POSITIVE LOGITS
     Developers
    0.85
     devs
    0.83
     roadmap
    0.83
     collaborate
    0.81
     KDE
    0.81
     Collabor
    0.81
     Labs
    0.78
     collabor
    0.76
     collaborating
    0.74
     workspace
    0.73
    Activations Density 0.182%

    No Known Activations