© 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. 10667
    Prev
    Next
    INDEX
    Explanations

    political terms related to power dynamics and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social hierarchy and dependency dynamics

    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
    ively
    -0.99
    sburg
    -0.89
    ispers
    -0.86
    rawdownloadcloneembedreportprint
    -0.83
    iveness
    -0.82
    osed
    -0.76
    artney
    -0.76
    maxwell
    -0.74
    adeon
    -0.74
    ains
    -0.73
    POSITIVE LOGITS
    hyde
    0.83
    doms
    0.75
     faults
    0.74
    yrinth
    0.73
    ller
    0.71
    ware
    0.70
     lodge
    0.70
    ck
    0.69
    ced
    0.68
    lda
    0.68
    Activations Density 0.082%

    No Known Activations