© 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. 6-RES-JB
    11. 9601
    Prev
    Next
    INDEX
    Explanations

    negations or contradictions

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases indicating the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ
    -0.75
    å¥
    -0.74
    æ©
    -0.73
    ç·
    -0.70
    LG
    -0.68
    ãĤ¼
    -0.67
    çļ
    -0.66
     Inventory
    -0.65
    ixel
    -0.64
    åº
    -0.64
    POSITIVE LOGITS
    hin
    1.18
    epad
    1.17
    icably
    1.17
     necessarily
    1.16
    icable
    1.14
     exactly
    1.00
     bothered
    0.94
     gonna
    0.94
    eworthy
    0.93
    orious
    0.93
    Activations Density 0.113%

    No Known Activations