© 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. 11-RES-JB
    11. 7555
    Prev
    Next
    INDEX
    Explanations

    dates associated with resignations from positions of power

    oai_token-act-pair · gpt-3.5-turbo

    instances of resignation or departure, often with detailed context such as dates or conditions of resignation

    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
     translates
    -0.68
    ounters
    -0.68
    gas
    -0.68
    amins
    -0.66
    insky
    -0.64
    Dispatch
    -0.62
    sburg
    -0.61
    erial
    -0.61
    ãĥ¼ãĤ¯
    -0.61
    horn
    -0.61
    POSITIVE LOGITS
     disgrace
    1.09
     unsatisf
    0.92
     resignation
    0.87
     dishon
    0.84
     disgust
    0.81
     citing
    0.80
     resign
    0.79
    ruct
    0.77
     protest
    0.75
     disagreement
    0.74
    Activations Density 0.200%

    No Known Activations