© 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. 6-RES-JB
    11. 3026
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to negation or exclusion

    oai_token-act-pair · gpt-3.5-turbo

    negations and words related to denial or contradiction

    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
    velt
    -0.79
    ç·
    -0.70
    eers
    -0.69
    stakes
    -0.68
     Companies
    -0.66
    FFER
    -0.65
    æ©
    -0.65
    oise
    -0.64
    assetsadobe
    -0.64
    pter
    -0.62
    POSITIVE LOGITS
    icably
    1.16
    eworthy
    1.14
    epad
    1.13
    orious
    1.13
    withstanding
    1.11
     necessarily
    1.04
    ional
    0.98
    ched
    0.95
    icable
    0.94
    ifications
    0.92
    Activations Density 0.093%

    No Known Activations