Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3315
    Prev
    Next
    INDEX
    Explanations

    names of political figures, especially those associated with a specific political campaign

    oai_token-act-pair · gpt-3.5-turbo

    names of political figures and their associated activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ratification
    -0.70
     Mortal
    -0.69
     debtor
    -0.69
     VID
    -0.65
     Jagu
    -0.62
    umar
    -0.60
    require
    -0.60
     Icar
    -0.58
    Ü
    -0.58
     licence
    -0.58
    POSITIVE LOGITS
    andowski
    0.99
     Spicer
    0.98
     Conway
    0.88
     aide
    0.85
     aides
    0.83
    verage
    0.83
    osta
    0.81
    ashington
    0.79
     Priebus
    0.79
    hler
    0.78
    Activations Density 0.030%

    No Known Activations