© 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. 9-RES-JB
    11. 18495
    Prev
    Next
    INDEX
    Explanations

    special characters or patterns

    oai_token-act-pair · gpt-3.5-turbo

    patterns of content related to safety and security issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     illusion
    -0.76
     footing
    -0.71
     charm
    -0.68
     whine
    -0.65
     immortal
    -0.65
     laughter
    -0.65
    tons
    -0.64
     wiser
    -0.63
     ageing
    -0.62
     empt
    -0.62
    POSITIVE LOGITS
    Additionally
    1.03
    Furthermore
    1.00
    ³³³³
    0.95
    Conclusion
    0.94
    ³³³³³³³³
    0.94
    ³³³³³³³³³³³³³³³³
    0.92
    Nevertheless
    0.90
    Regardless
    0.89
    Moreover
    0.88
    Nonetheless
    0.87
    Activations Density 0.394%

    No Known Activations