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. 0-RES-JB
    6. 4273
    Prev
    Next
    INDEX
    Explanations

    information sources or attributions in a text

    oai_token-act-pair · gpt-3.5-turbo

    citations or references to sources

    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
     monster
    -0.71
     choice
    -0.70
     mood
    -0.70
     turn
    -0.68
     pain
    -0.68
     affair
    -0.66
     act
    -0.66
     performance
    -0.66
     accent
    -0.66
     perfectly
    -0.65
    POSITIVE LOGITS
    Sources
    4.27
     Sources
    2.44
    References
    2.13
    Source
    1.75
     sources
    1.51
    ources
    1.48
    Resources
    1.39
    Appearances
    1.38
    Images
    1.36
    SOURCE
    1.35
    Activations Density 0.010%

    No Known Activations