© 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. 18505
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person named Rose

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Rose."

    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
    ulhu
    -0.89
    cffff
    -0.81
    etheless
    -0.78
    merce
    -0.73
    rongh
    -0.72
    redit
    -0.72
     fragmented
    -0.72
    binary
    -0.72
     accelerated
    -0.72
     restrictive
    -0.71
    POSITIVE LOGITS
    mary
    1.50
    anne
    1.12
    Rose
    1.09
    hill
    1.02
     Rose
    1.00
    mont
    0.97
    water
    0.94
    wood
    0.94
    lyn
    0.91
    xual
    0.89
    Activations Density 0.010%

    No Known Activations