© 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. 10-RES-JB
    11. 10139
    Prev
    Next
    INDEX
    Explanations

    positions of power and authority

    oai_token-act-pair · gpt-3.5-turbo

    references to authority and social or political structures

    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
    ppings
    -0.74
     Flavoring
    -0.71
    VERTISEMENT
    -0.70
    Alternatively
    -0.63
    azines
    -0.60
    })
    -0.60
    imeo
    -0.60
    luster
    -0.58
     Cosponsors
    -0.55
    SPONSORED
    -0.55
    POSITIVE LOGITS
    !!!!
    1.05
    !!!!!!!!
    1.02
    !!!
    1.00
     somewhere
    0.94
    !"
    0.93
     RIGHT
    0.92
     whose
    0.92
     EVERY
    0.90
     tonight
    0.90
    !!!!!
    0.88
    Activations Density 0.625%

    No Known Activations