© 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 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. 10-RES-JB
    11. 5873
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the absence of specific entities or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the absence or negation of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     anecd
    -0.75
     circa
    -0.74
     historically
    -0.73
     jointly
    -0.70
    inion
    -0.70
     debunked
    -0.69
    yrinth
    -0.68
    ivated
    -0.68
     endorsed
    -0.68
     extensively
    -0.68
    POSITIVE LOGITS
     difference
    0.86
     excuse
    0.80
     tomorrow
    0.80
     reason
    0.79
     temptation
    0.78
     repercussions
    0.77
     excuses
    0.77
     harm
    0.76
     danger
    0.76
     way
    0.75
    Activations Density 0.154%

    No Known Activations