Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 24329
    Prev
    Next
    INDEX
    Explanations

    terms related to laws, legislation, and politics, particularly focusing on bills being passed

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to legislative processes or passing bills

    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
     GOODMAN
    -0.70
    aiman
    -0.69
    ä¸ī
    -0.69
     Cortex
    -0.66
     ASP
    -0.64
     Swarm
    -0.63
     Delicious
    -0.59
     HUN
    -0.58
     SAM
    -0.58
    AAF
    -0.57
    POSITIVE LOGITS
    pass
    1.38
    enger
    1.28
    Pass
    1.21
    ioned
    1.15
    engers
    1.15
    wd
    1.10
    words
    0.97
    es
    0.97
    enhagen
    0.96
    edIn
    0.95
    Activations Density 0.005%

    No Known Activations