© 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. 9027
    Prev
    Next
    INDEX
    Explanations

    references to patriotism and national identity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a nation or country in a state of crisis or concern

    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
    NB
    -0.75
    INTER
    -0.73
    Tag
    -0.71
    TAG
    -0.70
     guiActiveUn
    -0.68
    ãĤ¨ãĥ«
    -0.67
    Event
    -0.66
    EStreamFrame
    -0.66
    REDACTED
    -0.66
    amination
    -0.65
    POSITIVE LOGITS
    wide
    1.04
    men
    0.90
    ICAN
    0.79
    liness
    0.75
    icans
    0.74
    thritis
    0.72
     electing
    0.72
    manship
    0.72
     Fathers
    0.71
    hood
    0.71
    Activations Density 0.093%

    No Known Activations