© 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. 6082
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation or contrast

    oai_token-act-pair · gpt-3.5-turbo

    the word "nor" and its various usages in the context of negation

    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
    DragonMagazine
    -0.63
    session
    -0.57
    mostly
    -0.56
    imil
    -0.56
     membr
    -0.55
    Voice
    -0.55
     Consortium
    -0.55
    Building
    -0.54
    staking
    -0.53
    igr
    -0.53
    POSITIVE LOGITS
    wegian
    1.06
     nor
    0.98
     anymore
    0.88
    theless
    0.84
    berto
    0.83
     any
    0.82
     necessarily
    0.81
    ajor
    0.79
    lihood
    0.78
     anywhere
    0.78
    Activations Density 0.029%

    No Known Activations