© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty but leaning towards acceptance of diversity and inclusivity, especially concerning LGBTQ+ rights and relationships

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

    instances of the word "for" indicating purposes or intended goals

    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
    ario
    -0.57
    odder
    -0.57
    Bloomberg
    -0.56
     frequ
    -0.55
    ji
    -0.54
    onde
    -0.53
    pi
    -0.53
     vacated
    -0.53
    yip
    -0.52
    DOWN
    -0.52
    POSITIVE LOGITS
     sure
    1.46
     certain
    1.14
    sure
    0.99
    ¶ħ
    0.98
    certain
    0.97
     yourselves
    0.97
     certainty
    0.93
     ourselves
    0.90
     definite
    0.83
     yourself
    0.82
    Activations Density 0.095%

    No Known Activations