© 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 EvalsExportsAPI 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. 9-RES-JB
    11. 18265
    Prev
    Next
    INDEX
    Explanations

    the word "supposed" followed by a verb or noun, indicating expectations or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expectations or societal norms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tex
    -0.66
    Ey
    -0.59
     Bohem
    -0.58
     Flavoring
    -0.58
    tein
    -0.57
     Blaz
    -0.57
     Splash
    -0.56
    sv
    -0.54
     Inventory
    -0.54
    lves
    -0.54
    POSITIVE LOGITS
    ALLY
    0.74
    ILY
    0.73
    ered
    0.68
    erest
    0.65
     "$:/
    0.64
    ivalent
    0.63
    escription
    0.63
    ich
    0.62
     to
    0.62
     bene
    0.61
    Activations Density 0.043%

    No Known Activations