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. 11-RES-JB
    6. 10143
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal action

    oai_token-act-pair · gpt-3.5-turbo

    content that discusses connections or associations to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lite
    -0.62
    dar
    -0.60
    uckland
    -0.57
    à¼
    -0.57
    oos
    -0.55
    ools
    -0.55
    ++)
    -0.54
    orable
    -0.54
    otted
    -0.54
    é¾įå
    -0.53
    POSITIVE LOGITS
     thereto
    1.15
     specifically
    0.98
     solely
    0.84
     to
    0.82
     principally
    0.79
     primarily
    0.78
     directly
    0.74
     exclusively
    0.74
     mainly
    0.70
    MpServer
    0.68
    Activations Density 0.071%

    No Known Activations