© 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. 11-RES-JB
    6. 18716
    Prev
    Next
    INDEX
    Explanations

    proper nouns representing individuals, particularly in the context of political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific political figures and their attributes

    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
    FTWARE
    -0.69
     Deadline
    -0.66
     sequential
    -0.66
     Variety
    -0.65
     Mechanics
    -0.65
     buzzing
    -0.65
     DSL
    -0.64
     Researchers
    -0.64
    Production
    -0.63
     Bulg
    -0.63
    POSITIVE LOGITS
     embodies
    1.37
     cares
    1.36
     opposes
    1.35
     understands
    1.30
     campaigned
    1.29
     lacks
    1.27
     represents
    1.23
     supports
    1.23
     disagrees
    1.16
     believes
    1.14
    Activations Density 0.258%

    No Known Activations