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. 16532
    Prev
    Next
    INDEX
    Explanations

    phrases related to effort, pride, and emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing responsibility, effort, and significance

    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
     sung
    -0.76
     delivered
    -0.72
    ramid
    -0.72
     handshake
    -0.71
    ntil
    -0.69
    ses
    -0.68
    tis
    -0.68
    existent
    -0.68
     erupt
    -0.66
     chained
    -0.65
    POSITIVE LOGITS
     emphasis
    1.04
     attention
    1.02
     responsibility
    0.94
    Notice
    0.86
     resources
    0.84
     blame
    0.84
     scrutiny
    0.82
     notice
    0.79
     effort
    0.77
    roach
    0.75
    Activations Density 0.197%

    No Known Activations