© 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. 2-RES-JB
    11. 4538
    Prev
    Next
    INDEX
    Explanations

    words related to heroism or being described as a hero

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a "hero."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aeda
    -1.00
    ateur
    -0.81
    imentary
    -0.75
    independent
    -0.70
    ntil
    -0.68
    creen
    -0.67
    olen
    -0.66
    ktop
    -0.65
    ossier
    -0.64
     millenn
    -0.64
    POSITIVE LOGITS
     hero
    1.06
     heroine
    0.93
    Hero
    0.93
    hero
    0.92
     heroes
    0.86
    ically
    0.85
    ku
    0.85
    ines
    0.77
    rities
    0.75
    士
    0.72
    Activations Density 0.010%

    No Known Activations