© 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. 7308
    Prev
    Next
    INDEX
    Explanations

    mentions of different locations and directions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of medical conditions or topics related to health

    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
     whilst
    -0.81
     negro
    -0.78
     english
    -0.77
    Firstly
    -0.76
    colour
    -0.70
     Whilst
    -0.68
    Contents
    -0.67
     fulfil
    -0.67
     tv
    -0.65
     cunt
    -0.65
    POSITIVE LOGITS
     nonprofits
    0.81
     regulators
    0.78
     anecd
    0.75
     federally
    0.74
     policymakers
    0.73
     anecdotal
    0.70
     advocates
    0.69
     pricey
    0.69
     nonprofit
    0.67
     automakers
    0.67
    Activations Density 1.729%

    No Known Activations