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. 4-RES-JB
    6. 3165
    Prev
    Next
    INDEX
    Explanations

    phrases related to political power and leadership

    oai_token-act-pair · gpt-3.5-turbo

    references to political power and its dynamics

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

    No Comments

    Negative Logits
    iths
    -0.73
    ead
    -0.70
    roma
    -0.69
    iotic
    -0.68
     Taste
    -0.66
    riad
    -0.66
    yip
    -0.66
    ogene
    -0.65
    ounty
    -0.65
    iar
    -0.65
    POSITIVE LOGITS
    houses
    0.95
     levers
    0.88
     vested
    0.83
     parity
    0.82
     consolidation
    0.77
    lessness
    0.77
    lifting
    0.75
     grid
    0.74
    puff
    0.74
     chords
    0.74
    Activations Density 0.027%

    No Known Activations