© 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. 8-RES-JB
    11. 22653
    Prev
    Next
    INDEX
    Explanations

    legal and political terms or phrases, such as specific court cases or government actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to governance and legal matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.77
    ij士
    -0.64
     âĶľâĶĢâĶĢ
    -0.58
    eday
    -0.57
     Alternatively
    -0.56
    thens
    -0.56
    ãĥ¯
    -0.56
    ividually
    -0.54
    tml
    -0.54
     oneself
    -0.54
    POSITIVE LOGITS
     debacle
    0.99
     fiasco
    0.98
     controversy
    0.92
     takeover
    0.89
     scandal
    0.86
     onslaught
    0.85
     crackdown
    0.85
     refusal
    0.84
     shortcomings
    0.83
     blockade
    0.83
    Activations Density 0.834%

    No Known Activations