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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 19376
    Prev
    Next
    INDEX
    Explanations

    words related to dryness or things that are dry

    oai_token-act-pair · gpt-3.5-turbo

    words related to dryness

    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
     Fortress
    -0.75
     Exercise
    -0.67
     GOODMAN
    -0.65
     MacDonald
    -0.65
     Buch
    -0.64
    querade
    -0.62
     ÃĹ
    -0.62
     Enter
    -0.61
    listed
    -0.60
     CN
    -0.60
    POSITIVE LOGITS
     dri
    3.90
    dri
    1.95
     drip
    1.77
     Dri
    1.68
     dripping
    1.52
     drib
    1.42
     dry
    1.28
     ooz
    1.27
     drying
    1.26
     sprink
    1.26
    Activations Density 0.032%

    No Known Activations