© 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. 11-RES-JB
    11. 3498
    Prev
    Next
    INDEX
    Explanations

    negations

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases that denote a denial of something

    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
    kamp
    -0.76
    rift
    -0.64
    umbn
    -0.61
    è¦ļéĨĴ
    -0.60
    papers
    -0.58
    igans
    -0.58
    stakes
    -0.58
    plate
    -0.57
    ancial
    -0.56
    iewicz
    -0.54
    POSITIVE LOGITS
    withstanding
    1.34
    eworthy
    1.30
     surprisingly
    1.23
    ably
    1.22
    icing
    1.17
    orious
    1.15
    ices
    1.01
     everyone
    1.01
     only
    0.97
    icably
    0.96
    Activations Density 0.057%

    No Known Activations