© 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. 4-RES-JB
    11. 7071
    Prev
    Next
    INDEX
    Explanations

    phrases related to business strategy and decision-making

    oai_token-act-pair · gpt-3.5-turbo

    various punctuation and phrase structures signifying points of emphasis or emotional expressions

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

    No Comments

    Negative Logits
     cartel
    -0.75
     sacked
    -0.75
     ratified
    -0.71
     axe
    -0.71
     consulate
    -0.71
     gunfire
    -0.70
     amph
    -0.70
     embassy
    -0.69
     legally
    -0.67
     amnesty
    -0.66
    POSITIVE LOGITS
    Examples
    1.14
    Example
    1.09
    Conclusion
    1.02
    Therefore
    1.02
    Different
    1.01
    Avoid
    1.00
    Learn
    0.99
    Understanding
    0.99
    Consider
    0.99
    Recommended
    0.98
    Activations Density 0.662%

    No Known Activations