© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17302
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or viewpoints

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech and reported dialogue

    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
     egalitarian
    -0.70
     favored
    -0.66
     utopian
    -0.65
     millennium
    -0.64
     famously
    -0.63
     millennia
    -0.63
     fashionable
    -0.62
     favoring
    -0.62
     wealthier
    -0.61
     niche
    -0.61
    POSITIVE LOGITS
     enqu
    1.11
    Officers
    0.97
     investigation
    0.95
     CCTV
    0.95
    police
    0.92
    Reports
    0.91
     confir
    0.88
     investigations
    0.88
     briefed
    0.88
     RCMP
    0.88
    Activations Density 0.617%

    No Known Activations