© 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. 4-RES-JB
    11. 3652
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of overturning legal decisions or rulings

    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
    ebus
    -0.78
    artney
    -0.72
    uld
    -0.71
    NetMessage
    -0.68
    ymph
    -0.67
    cific
    -0.66
    OTOS
    -0.66
     Dise
    -0.66
    mpeg
    -0.65
    ÃŁ
    -0.64
    POSITIVE LOGITS
     overturned
    1.01
     overturn
    0.91
     verdict
    0.78
     rulings
    0.70
    ragon
    0.66
     reversed
    0.66
    hurst
    0.66
    rules
    0.63
    eering
    0.63
     unanimously
    0.63
    Activations Density 0.021%

    No Known Activations