© 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. 5592
    Prev
    Next
    INDEX
    Explanations

    the name "Cole" at varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cole."

    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
    oppable
    -0.68
    ĺħ
    -0.65
    channelAvailability
    -0.64
    ocre
    -0.64
     guiActiveUn
    -0.62
    hots
    -0.61
    oslav
    -0.61
     nomine
    -0.60
    ģ
    -0.59
    >>\
    -0.58
    POSITIVE LOGITS
    tto
    1.09
    brate
    0.86
    opter
    0.84
    tti
    0.84
     Porter
    0.80
    mons
    0.79
    opsis
    0.78
    phrine
    0.75
    bourne
    0.75
    lette
    0.74
    Activations Density 0.033%

    No Known Activations