© 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. 10778
    Prev
    Next
    INDEX
    Explanations

    words related to entities, organizations, and proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to politics, organizations, and social issues

    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
    ocious
    -0.74
    ategory
    -0.72
    utral
    -0.69
    geries
    -0.68
    entanyl
    -0.66
    arnaev
    -0.65
    maxwell
    -0.65
    iltration
    -0.65
     Leilan
    -0.65
    arp
    -0.64
    POSITIVE LOGITS
     deems
    1.12
     deem
    0.87
     ought
    0.85
     might
    0.82
     sorely
    0.81
     couldn
    0.80
     should
    0.80
     could
    0.78
     would
    0.78
     lacked
    0.76
    Activations Density 0.331%

    No Known Activations