© 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. 13646
    Prev
    Next
    INDEX
    Explanations

    adjective-noun combinations that express negative judgement

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to societal issues and behaviors

    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
    ften
    -0.73
    ittee
    -0.71
    anwhile
    -0.70
     THERE
    -0.68
     smelled
    -0.66
    ilk
    -0.64
    ocket
    -0.64
     Originally
    -0.63
    uden
    -0.63
    orest
    -0.63
    POSITIVE LOGITS
     situations
    0.93
     proportions
    0.84
     amounts
    0.83
     ideas
    0.80
     ones
    0.80
     levels
    0.79
     interpretations
    0.79
     circumstances
    0.78
     opportunities
    0.77
     truths
    0.77
    Activations Density 0.502%

    No Known Activations