Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 12879
    Prev
    Next
    INDEX
    Explanations

    adjectives related to dryness

    oai_token-act-pair · gpt-3.5-turbo

    references to dry conditions or states

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

    No Comments

    Negative Logits
    emonium
    -0.86
    aurus
    -0.80
    aepernick
    -0.77
    asketball
    -0.76
    CVE
    -0.76
    ority
    -0.75
    raltar
    -0.74
    allery
    -0.73
    ortun
    -0.73
    utterstock
    -0.73
    POSITIVE LOGITS
    ness
    0.91
    wall
    0.88
     dry
    0.79
    cloth
    0.77
    burn
    0.76
     drying
    0.76
     hump
    0.74
     cleaner
    0.72
    clean
    0.72
    waters
    0.72
    Activations Density 0.009%

    No Known Activations