© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3577
    Prev
    Next
    INDEX
    Explanations

    names, specifically the name "Dustin"

    oai_token-act-pair · gpt-3.5-turbo

    names and references to individuals named Dustin

    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
    ilitary
    -1.02
    ————
    -0.84
    pering
    -0.83
    ciation
    -0.83
    meric
    -0.81
    bara
    -0.81
    ilk
    -0.80
    alg
    -0.80
    hare
    -0.80
    hell
    -0.79
    POSITIVE LOGITS
     Brow
    0.68
    endor
    0.68
    ocity
    0.64
     galleries
    0.63
    iction
    0.62
    icit
    0.62
     Timbers
    0.62
    orian
    0.62
     Objects
    0.62
    uminati
    0.61
    Activations Density 0.045%

    No Known Activations