© 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. 2-RES-JB
    11. 13261
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Cory"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Cory."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    slave
    -0.68
     discipl
    -0.64
     vested
    -0.64
     inadequ
    -0.63
    animous
    -0.62
    Haunted
    -0.62
    ा
    -0.61
    qualified
    -0.60
     validation
    -0.60
     discriminating
    -0.60
    POSITIVE LOGITS
    pheus
    0.99
     Cory
    0.97
    nan
    0.85
    mons
    0.85
    caster
    0.84
    zon
    0.81
     Nich
    0.80
    stal
    0.78
     Rasm
    0.78
     Booker
    0.77
    Activations Density 0.010%

    No Known Activations