© 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. 7-RES-JB
    11. 4884
    Prev
    Next
    INDEX
    Explanations

    names of government officials, leaders, and executives

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sold
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    acters
    -0.65
    =$
    -0.61
    versive
    -0.61
     Palestin
    -0.60
     resil
    -0.60
    Load
    -0.59
     Lov
    -0.59
    RIP
    -0.59
    POSITIVE LOGITS
     Jr
    1.06
     oversaw
    0.98
     oversees
    0.94
    oglu
    0.93
     urged
    0.88
     presided
    0.88
     announced
    0.87
     III
    0.85
     Sr
    0.85
     acknowledged
    0.85
    Activations Density 0.239%

    No Known Activations