© 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. 9-RES-JB
    11. 17474
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal reasoning such as "reasonable doubt"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of reasonableness or justification

    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
    rael
    -0.76
    uria
    -0.73
    chu
    -0.72
    chin
    -0.72
    aukee
    -0.68
    yang
    -0.67
    yi
    -0.67
    ocket
    -0.67
    lets
    -0.65
    Interstitial
    -0.64
    POSITIVE LOGITS
     expectation
    0.97
     priced
    0.93
     doubt
    0.91
     expectations
    0.91
     accommodation
    0.90
     approximation
    0.86
     sized
    0.85
     suspicion
    0.83
     accommodations
    0.82
     inference
    0.82
    Activations Density 0.059%

    No Known Activations