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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8926
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the word "el"

    oai_token-act-pair · gpt-3.5-turbo

    the term "elixir" and its variations across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ®å
    -0.75
     Crunch
    -0.74
    ãĥ´ãĤ¡
    -0.72
    Kit
    -0.72
     Analytics
    -0.72
     Depot
    -0.71
    æĸ¹
    -0.69
    Shot
    -0.69
    uyomi
    -0.69
     Continued
    -0.69
    POSITIVE LOGITS
    izabeth
    1.12
    ixir
    1.01
    iquid
    0.95
     el
    0.91
    igible
    0.88
    ibrary
    0.84
    inement
    0.84
    ijah
    0.80
    usive
    0.79
    ivas
    0.78
    Activations Density 0.006%

    No Known Activations