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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 2-RES-JB
    6. 16373
    Prev
    Next
    INDEX
    Explanations

    phrases related to federal government actions and funding

    oai_token-act-pair · gpt-3.5-turbo

    references to federal government funding and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clever
    -0.85
    lihood
    -0.81
     Survive
    -0.77
    enger
    -0.77
    pter
    -0.75
     Tycoon
    -0.74
    ++++
    -0.74
    zzo
    -0.74
    bringer
    -0.74
    hops
    -0.73
    POSITIVE LOGITS
     appellate
    1.04
     government
    0.99
     judiciary
    0.91
     agencies
    0.86
     statute
    0.83
     legislation
    0.81
     judicial
    0.81
     federal
    0.80
     law
    0.80
     governmental
    0.79
    Activations Density 0.022%

    No Known Activations