© 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. 11-RES-JB
    11. 618
    Prev
    Next
    INDEX
    Explanations

    phrases related to national identity in a critical context

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "this country" indicating themes of national identity and social issues

    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
    acers
    -0.78
     Pwr
    -0.78
    Examples
    -0.76
    thumbnails
    -0.73
    apses
    -0.72
    ATURES
    -0.70
    gans
    -0.69
     proofs
    -0.67
    poons
    -0.66
    anyahu
    -0.66
    POSITIVE LOGITS
     country
    1.41
     nation
    1.11
     hemisphere
    1.11
     continent
    1.10
     century
    1.10
     planet
    1.04
     magnificent
    1.03
     wonderful
    0.99
    country
    0.97
     generation
    0.94
    Activations Density 0.127%

    No Known Activations