© 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 EvalsExportsinterp-engineNEWAPI 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. 5172
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships or connections between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and friendships

    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
    cale
    -0.75
    etting
    -0.74
    ourcing
    -0.73
    creen
    -0.71
    lam
    -0.70
    Interstitial
    -0.69
    hovah
    -0.69
    hur
    -0.68
    OME
    -0.67
    ettings
    -0.67
    POSITIVE LOGITS
     Jaime
    0.80
     Sophie
    0.77
    liness
    0.76
    mates
    0.76
     counterparts
    0.75
     Hannah
    0.72
     Nicholas
    0.71
     Stephanie
    0.71
     peers
    0.71
     Richard
    0.70
    Activations Density 0.162%

    No Known Activations