© 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. 17630
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and self-reflection

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal determination and resilience

    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
    encies
    -0.77
     GOODMAN
    -0.73
    tesy
    -0.72
     Utilities
    -0.71
    entials
    -0.71
    roversial
    -0.71
    mination
    -0.69
     Monthly
    -0.68
    pmwiki
    -0.68
    rates
    -0.68
    POSITIVE LOGITS
     reborn
    1.42
     enslaved
    1.28
     trapped
    1.28
     powerless
    1.26
     immersed
    1.20
     healed
    1.20
     liberated
    1.19
     alive
    1.18
     invincible
    1.18
     imprisoned
    1.15
    Activations Density 0.231%

    No Known Activations