© 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. 8-RES-JB
    11. 12372
    Prev
    Next
    INDEX
    Explanations

    positive affirmations or expressions of good fortune

    oai_token-act-pair · gpt-3.5-turbo

    expressions of luck and positive outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.79
    itatively
    -0.74
    apo
    -0.72
    raising
    -0.72
    eworthy
    -0.70
    HUD
    -0.69
    ieu
    -0.66
    orically
    -0.65
    ivably
    -0.64
    cut
    -0.64
    POSITIVE LOGITS
     awoken
    0.80
     succumbed
    0.77
     luckily
    0.74
     succeeded
    0.73
     fortunately
    0.72
     somew
    0.70
     managed
    0.69
     survives
    0.68
     thankfully
    0.68
     forgot
    0.68
    Activations Density 0.316%

    No Known Activations