© 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. 8-RES-JB
    11. 9479
    Prev
    Next
    INDEX
    Explanations

    words related to specific names, possibly proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Ta."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lessly
    -0.79
    sburgh
    -0.66
     OCD
    -0.64
     Ashes
    -0.63
     ANGEL
    -0.62
    Ö¼
    -0.62
     atmosphere
    -0.62
     injection
    -0.60
     CRC
    -0.60
     representations
    -0.59
    POSITIVE LOGITS
    plin
    1.31
    iba
    1.23
    vern
    1.08
    fts
    1.08
    pling
    1.08
    oshi
    1.03
    onga
    1.01
    ifa
    0.98
    uren
    0.97
    ft
    0.96
    Activations Density 0.018%

    No Known Activations