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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18330
    Prev
    Next
    INDEX
    Explanations

    words related to dryness

    oai_token-act-pair · gpt-3.5-turbo

    references to dry conditions or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.84
    emonium
    -0.81
    allery
    -0.79
    aepernick
    -0.79
    asketball
    -0.79
    aurus
    -0.78
    raltar
    -0.78
    ourage
    -0.77
    auri
    -0.77
    "]=>
    -0.77
    POSITIVE LOGITS
    wall
    0.93
     dry
    0.86
    ness
    0.86
     drying
    0.82
    dry
    0.80
    burn
    0.80
     bulb
    0.74
    wallet
    0.74
    cloth
    0.73
    stal
    0.72
    Activations Density 0.008%

    No Known Activations