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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 4507
    Prev
    Next
    INDEX
    Explanations

    phrases surrounded by unique symbols like "âĢĶ" which could possibly indicate a specific context or topic

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to cybersecurity issues and data privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.84
    omorphic
    -0.79
    iple
    -0.76
     proced
    -0.73
     precaution
    -0.72
     loft
    -0.70
    oby
    -0.69
     suspic
    -0.68
    ©¶æ
    -0.68
    egu
    -0.67
    POSITIVE LOGITS
    feat
    1.04
    ––
    1.00
    along
    0.94
    particularly
    0.92
    âĢ¢âĢ¢
    0.90
    sil
    0.89
    advertisement
    0.89
    they
    0.88
    meaning
    0.87
    including
    0.86
    Activations Density 0.043%

    No Known Activations