© 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. 9-RES-JB
    11. 3222
    Prev
    Next
    INDEX
    Explanations

    terms related to survival and thriving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to survival or the act of enduring difficult conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ©Ł
    -0.77
    med
    -0.73
    othy
    -0.71
    iple
    -0.69
    metry
    -0.66
    å°Ĩ
    -0.66
    ãĥİ
    -0.65
    awatts
    -0.64
    leased
    -0.63
    arc
    -0.63
    POSITIVE LOGITS
     adversity
    0.87
     unsc
    0.86
     digestion
    0.83
     patiently
    0.82
     intact
    0.81
     infancy
    0.79
     relegation
    0.77
     Hurricanes
    0.73
     hardships
    0.72
    ably
    0.72
    Activations Density 0.052%

    No Known Activations