© 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. 3-RES-JB
    11. 12706
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the name "ars"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "ars."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Thompson
    -0.65
    sylv
    -0.62
    buquerque
    -0.60
     Yankee
    -0.59
    states
    -0.59
     joking
    -0.58
     stret
    -0.58
     STATES
    -0.58
     Vermont
    -0.57
     oxid
    -0.57
    POSITIVE LOGITS
    hip
    1.20
    hips
    1.17
    mith
    1.08
    ystem
    0.98
    omething
    0.97
    ansas
    0.96
    imony
    0.93
    hod
    0.93
    itect
    0.91
    itans
    0.87
    Activations Density 0.013%

    No Known Activations