© 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. 0-RES-JB
    11. 8292
    Prev
    Next
    INDEX
    Explanations

    descriptive text related to strong desires and intentions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "desire" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiz
    -0.68
    busters
    -0.68
    aster
    -0.65
    Newsletter
    -0.63
    inning
    -0.62
    ummies
    -0.62
    guards
    -0.61
     GMT
    -0.61
    oli
    -0.60
    iatrics
    -0.60
    POSITIVE LOGITS
     desire
    3.43
     desires
    2.25
     Desire
    1.82
     thirst
    1.79
     willingness
    1.76
     longing
    1.71
     wish
    1.67
     inclination
    1.65
     craving
    1.62
     appetite
    1.57
    Activations Density 0.014%

    No Known Activations