© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 11-RES-JB
    11. 12684
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a choice between options

    oai_token-act-pair · gpt-3.5-turbo

    references to options and suggestions for actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    */(
    -0.63
     partName
    -0.60
     Arri
    -0.58
     predomin
    -0.57
     Beir
    -0.57
    idden
    -0.56
    eatures
    -0.55
    terness
    -0.54
    ospace
    -0.54
    idth
    -0.54
    POSITIVE LOGITS
     can
    1.63
     could
    1.59
    could
    1.49
    can
    1.45
    Could
    1.10
     Can
    1.06
    Can
    1.05
     CAN
    1.02
     Could
    0.97
     able
    0.95
    Activations Density 0.762%

    No Known Activations