© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18566
    Prev
    Next
    INDEX
    Explanations

    the concept of 'Life'

    oai_token-act-pair · gpt-3.5-turbo

    variations of the phrase "Life is" followed by various descriptions or conditions

    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
    rouse
    -0.78
    ESE
    -0.73
    ieth
    -0.72
     Cosponsors
    -0.72
    iates
    -0.72
    porate
    -0.71
    inges
    -0.71
    EMA
    -0.67
    ittee
    -0.66
    rpm
    -0.65
    POSITIVE LOGITS
     fleeting
    0.96
     ours
    0.96
     yours
    0.96
     finite
    0.93
     unpredictable
    0.93
     infinite
    0.92
     fragile
    0.91
     eternal
    0.90
     gonna
    0.88
     timeless
    0.88
    Activations Density 0.188%

    No Known Activations