© 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. 12-RES-JB
    11. 2860
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a verb in the base form

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the second person, particularly the word "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFIED
    -0.85
    PRES
    -0.70
    ULTS
    -0.68
    WithNo
    -0.68
    letters
    -0.67
    Cho
    -0.66
    CLUD
    -0.66
     millenn
    -0.66
    ONSORED
    -0.66
    orses
    -0.64
    POSITIVE LOGITS
     proceed
    0.97
     await
    0.97
     move
    0.95
     navigate
    0.94
     approach
    0.92
     traverse
    0.92
     contemplate
    0.89
     prepare
    0.89
     progress
    0.88
     embark
    0.88
    Activations Density 0.072%

    No Known Activations