© 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. 20168
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal settings or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to courthouses or legal settings

    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
    umar
    -0.84
    hy
    -0.75
    olls
    -0.75
    lust
    -0.75
    ku
    -0.73
    growth
    -0.73
    hell
    -0.72
    sen
    -0.72
    loss
    -0.71
    lihood
    -0.71
    POSITIVE LOGITS
     courthouse
    1.37
    thouse
    1.10
     plaza
    0.88
     chapel
    0.85
     Pengu
    0.84
     courtyard
    0.83
     clerk
    0.83
     gates
    0.82
     courtroom
    0.81
     Plaza
    0.80
    Activations Density 0.002%

    No Known Activations