© 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. 1-RES-JB
    11. 10363
    Prev
    Next
    INDEX
    Explanations

    negations or contradictions in sentences

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases that express something is not true or absent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inventory
    -0.75
    former
    -0.68
    eur
    -0.66
    stakes
    -0.65
    inav
    -0.65
    itor
    -0.65
    eers
    -0.63
     Handbook
    -0.63
    Origin
    -0.63
    itance
    -0.63
    POSITIVE LOGITS
     necessarily
    1.28
    icably
    1.24
    epad
    1.03
    icable
    1.02
    withstanding
    1.00
     yet
    0.89
     exactly
    0.87
    orious
    0.87
     bothering
    0.86
    necess
    0.85
    Activations Density 0.198%

    No Known Activations