© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8-RES-JB
    11. 17796
    Prev
    Next
    INDEX
    Explanations

    phrases indicating negation

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing negation or absence of effect

    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
     palms
    -0.76
     Hok
    -0.71
     Printed
    -0.68
     CoC
    -0.63
     Ages
    -0.61
    case
    -0.61
     Seasons
    -0.61
    boarding
    -0.61
    hog
    -0.61
     Handling
    -0.59
    POSITIVE LOGITS
    ppel
    1.08
    omsday
    1.00
    vet
    0.98
     not
    0.94
    herty
    0.92
    pez
    0.92
    ozy
    0.89
    oms
    0.89
     NOT
    0.89
     exist
    0.89
    Activations Density 0.096%

    No Known Activations