© 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. 11-RES-JB
    11. 14956
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics and news

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.75
    _.
    -0.71
    CONCLUS
    -0.70
    States
    -0.66
    tics
    -0.66
     destro
    -0.64
    6000
    -0.63
     smugglers
    -0.63
    Closure
    -0.62
    MU
    -0.62
    POSITIVE LOGITS
     embattled
    0.78
     Donald
    0.68
     superstar
    0.63
    dinand
    0.61
     Antonio
    0.60
     John
    0.60
     Adolf
    0.60
     iconic
    0.59
     Tim
    0.58
     ...
    0.57
    Activations Density 0.283%

    No Known Activations