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. 11-RES-JB
    6. 4527
    Prev
    Next
    INDEX
    Explanations

    references to government action and societal issues

    oai_token-act-pair · gpt-3.5-turbo

    themes related to morality and human connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scheduled
    -0.57
     Pipeline
    -0.54
     pipeline
    -0.54
     Plaza
    -0.53
    UMP
    -0.53
     Alley
    -0.52
     logging
    -0.52
     marquee
    -0.52
     Nickel
    -0.52
     headline
    -0.52
    POSITIVE LOGITS
     righteousness
    0.98
     thou
    0.84
     hath
    0.83
     immortality
    0.83
     everlasting
    0.83
     unto
    0.82
     pleasures
    0.81
     sinners
    0.81
     souls
    0.81
     Thou
    0.80
    Activations Density 0.883%

    No Known Activations