© 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. 10200
    Prev
    Next
    INDEX
    Explanations

    phrases related to someone's rise in fame or power

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving rising to prominence or elevated status

    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
    tun
    -0.67
    reb
    -0.67
    tenance
    -0.66
    ice
    -0.66
    grain
    -0.63
    loop
    -0.62
    eva
    -0.61
     postponed
    -0.60
    ta
    -0.60
    going
    -0.57
    POSITIVE LOGITS
     prominence
    1.57
     notoriety
    1.15
     fame
    1.12
     heights
    1.12
     adulthood
    1.04
     greatness
    1.03
     unbeliev
    1.01
     relevance
    0.95
     stature
    0.94
    wered
    0.93
    Activations Density 0.158%

    No Known Activations