© 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. 1-RES-JB
    11. 20160
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and constitutional matters

    oai_token-act-pair · gpt-3.5-turbo

    references to the Constitution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hao
    -0.76
    vol
    -0.71
    iter
    -0.71
    val
    -0.70
    VIS
    -0.70
    inventory
    -0.67
    joy
    -0.66
    visible
    -0.66
    Urban
    -0.65
    ign
    -0.65
    POSITIVE LOGITS
     Constitution
    1.01
     Amendments
    0.90
    eering
    0.82
    arium
    0.81
     Clause
    0.80
     Amendment
    0.80
    isphere
    0.78
     Seym
    0.73
    folios
    0.72
    naire
    0.72
    Activations Density 0.008%

    No Known Activations