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. 1-RES-JB
    6. 12691
    Prev
    Next
    INDEX
    Explanations

    the word "el" in texts

    oai_token-act-pair · gpt-3.5-turbo

    the specific substring "el" within words

    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
    displayText
    -0.93
    ItemTracker
    -0.83
     Sprite
    -0.70
    SourceFile
    -0.65
     sugg
    -0.65
    SpaceEngineers
    -0.64
    uyomi
    -0.63
    alez
    -0.63
    é¾įå¥ij士
    -0.62
     Pool
    -0.59
    POSITIVE LOGITS
    izabeth
    1.15
    itic
    1.05
    estial
    0.97
    baum
    0.95
    ivery
    0.95
    ength
    0.91
    iberal
    0.90
    ayer
    0.90
    ibrary
    0.89
    holm
    0.89
    Activations Density 0.024%

    No Known Activations