© 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. 6-RES-JB
    11. 14646
    Prev
    Next
    INDEX
    Explanations

    mentions of domestic-related terms or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to "domestic" issues or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.96
    uyomi
    -0.93
    */(
    -0.83
    umper
    -0.82
    ombs
    -0.78
    osen
    -0.78
    edin
    -0.75
    kson
    -0.74
     GOODMAN
    -0.74
    atto
    -0.74
    POSITIVE LOGITS
     Violence
    1.02
     affairs
    0.94
     violence
    0.93
     tranqu
    0.86
     appliances
    0.81
    violence
    0.79
     combustion
    0.77
     terrorism
    0.76
    estic
    0.75
    ility
    0.73
    Activations Density 0.023%

    No Known Activations