© 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. 5065
    Prev
    Next
    INDEX
    Explanations

    words related to famous names or figures

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names associated with music and entertainment figures

    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
    pter
    -0.78
    ources
    -0.77
    earch
    -0.75
     flare
    -0.71
    emis
    -0.70
    individual
    -0.67
     Lauder
    -0.66
     oppos
    -0.66
    occup
    -0.66
    actionDate
    -0.65
    POSITIVE LOGITS
     Bourbon
    0.73
     Cookie
    0.73
    zees
    0.71
    glers
    0.66
     Cookies
    0.66
    ingo
    0.66
    uckle
    0.64
    abba
    0.63
    itty
    0.62
    theless
    0.62
    Activations Density 0.351%

    No Known Activations