© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions or regulations

    oai_token-act-pair · gpt-3.5-turbo

    segments of text related to taxation and financial regulation

    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
     fulfil
    -0.81
     adolesc
    -0.76
     attent
    -0.70
     endeavour
    -0.70
     duty
    -0.68
     Reincarnated
    -0.68
     endeav
    -0.68
     himself
    -0.68
    iversary
    -0.67
    aviour
    -0.65
    POSITIVE LOGITS
    Advertisement
    1.05
    ccording
    1.05
    SPONSORED
    1.02
    Their
    0.98
    Companies
    0.94
    Newsletter
    0.93
    Bloomberg
    0.92
    Contribut
    0.90
    Related
    0.90
    ADVERTISEMENT
    0.89
    Activations Density 0.984%

    No Known Activations