© 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. 11163
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to legal or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Roberts" and its variations in the context of legal or political discussions

    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
    earable
    -0.82
     Poles
    -0.66
     Extend
    -0.64
    icago
    -0.64
    bernatorial
    -0.63
    iop
    -0.63
    ascar
    -0.62
    illary
    -0.62
    abetes
    -0.61
    emonic
    -0.60
    POSITIVE LOGITS
    hetti
    0.76
    bart
    0.74
    rary
    0.72
    stall
    0.72
    heastern
    0.72
    DOM
    0.72
    chn
    0.70
    âĸĪâĸĪ
    0.69
    burg
    0.67
    Wil
    0.67
    Activations Density 0.049%

    No Known Activations