© 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. 1-RES-JB
    11. 13532
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or entities being described as "supreme"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "supreme" and other related hierarchical or authoritative terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OUT
    -0.75
    ppo
    -0.73
    TPS
    -0.72
     Cro
    -0.70
     Shed
    -0.67
    ARP
    -0.67
     Flint
    -0.67
     Hoffman
    -0.67
     Widow
    -0.67
     Dro
    -0.66
    POSITIVE LOGITS
    reme
    0.92
    tarian
    0.89
     referen
    0.88
     supreme
    0.87
    ly
    0.86
    iour
    0.79
    tre
    0.78
     vigilance
    0.77
    rament
    0.77
    law
    0.77
    Activations Density 0.003%

    No Known Activations