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

    Neuronpedia

    Jacobian LensNEW
    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. 16587
    Prev
    Next
    INDEX
    Explanations

    times or events related to political figures, particularly within a specific context of activities or mentions involving certain people or groups

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    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
     Tud
    -1.00
     Rud
    -0.97
     OD
    -0.90
     Judd
    -0.87
     Tib
    -0.87
     Sud
    -0.83
     OCT
    -0.83
     Nost
    -0.82
     Treaty
    -0.78
     Rudolph
    -0.78
    POSITIVE LOGITS
    el
    1.25
    75
    1.24
    EL
    1.22
    els
    1.17
    elman
    1.07
    ELS
    1.04
    elope
    1.01
    ela
    1.01
    azel
    0.98
    eling
    0.97
    Activations Density 0.296%

    No Known Activations