© 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. 3264
    Prev
    Next
    INDEX
    Explanations

    expressions related to love and farewell messages

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

    expressions of love and remembrance related to loss

    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
    ONSORED
    -0.79
    ß
    -0.72
    ĸļ士
    -0.71
    Kids
    -0.71
    Magikarp
    -0.70
    ļéĨĴ
    -0.70
    Nick
    -0.70
    Loading
    -0.69
    ÃįÃį
    -0.69
    ENC
    -0.69
    POSITIVE LOGITS
     hath
    1.19
     rejoice
    1.13
     livest
    1.09
     esteem
    1.08
     deceive
    1.07
     dw
    1.05
     perish
    1.04
     shall
    1.04
     endeavour
    1.03
     conceive
    1.03
    Activations Density 0.223%

    No Known Activations