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. 8-RES-JB
    6. 455
    Prev
    Next
    INDEX
    Explanations

    phrases related to running for political positions

    oai_token-act-pair · gpt-3.5-turbo

    references to personal stakes or individual interests in competitive contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.82
    erers
    -0.71
     Sorce
    -0.63
     Matter
    -0.62
    ilst
    -0.61
    sted
    -0.59
     Circ
    -0.58
     Span
    -0.58
    emed
    -0.57
    venants
    -0.57
    POSITIVE LOGITS
     sake
    1.17
     elusive
    0.89
     forgiveness
    0.81
     jug
    0.80
     immortality
    0.79
     underdog
    0.77
    ummies
    0.77
     coveted
    0.75
    ulz
    0.75
    aughs
    0.74
    Activations Density 0.474%

    No Known Activations