© 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. 10-RES-JB
    11. 11142
    Prev
    Next
    INDEX
    Explanations

    legal or regulatory terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulatory discussions and trade effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    big
    -0.80
     bigger
    -0.78
    maybe
    -0.77
     scared
    -0.74
    think
    -0.74
    elight
    -0.74
     luckily
    -0.73
    something
    -0.73
     stuff
    -0.73
     harder
    -0.70
    POSITIVE LOGITS
     Examination
    0.94
     embodiments
    0.93
     Defendants
    0.88
     Applicant
    0.87
     persons
    0.85
     SCP
    0.85
     Selected
    0.85
     Plaint
    0.84
     appell
    0.84
     appellant
    0.83
    Activations Density 0.735%

    No Known Activations