© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10755
    Prev
    Next
    INDEX
    Explanations

    economic and political terms related to government policies and regulations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating definitions, clarifications, or significant outcomes regarding issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saying
    -0.54
    ammy
    -0.52
    laugh
    -0.52
    anmar
    -0.51
    ruary
    -0.50
    aughed
    -0.50
     councill
    -0.49
    shoot
    -0.49
    IFT
    -0.47
    ò
    -0.46
    POSITIVE LOGITS
     is
    1.53
     exceeds
    1.42
     belongs
    1.39
     awaits
    1.39
     represents
    1.37
     constitutes
    1.37
     has
    1.37
     exists
    1.37
     lacks
    1.34
     remains
    1.34
    Activations Density 1.189%

    No Known Activations