© 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. 10-RES-JB
    11. 17443
    Prev
    Next
    INDEX
    Explanations

    words related to the act of observing or watching

    oai_token-act-pair · gpt-3.5-turbo

    terms related to observation and monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lins
    -0.76
    boss
    -0.74
    anyl
    -0.72
    illard
    -0.71
    Interstitial
    -0.70
    zzy
    -0.69
    cit
    -0.68
    recy
    -0.67
    ifice
    -0.65
    tering
    -0.64
    POSITIVE LOGITS
     observer
    0.94
     observation
    0.93
     observers
    0.88
     observing
    0.87
     Observ
    0.82
     Telescope
    0.78
     monitored
    0.74
     observe
    0.74
     observations
    0.73
     observable
    0.73
    Activations Density 0.067%

    No Known Activations