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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 19592
    Prev
    Next
    INDEX
    Explanations

    phrases related to official confirmations or nominations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the confirmation process of nominees in a political context

    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
     econom
    -0.77
    ijk
    -0.76
    lag
    -0.69
    olver
    -0.67
    ibaba
    -0.66
    MQ
    -0.66
     Spiegel
    -0.66
    Pak
    -0.64
    CBC
    -0.63
     Mecca
    -0.63
    POSITIVE LOGITS
     nominees
    1.24
     nominations
    1.06
     secretaries
    1.05
     appoint
    0.98
     nominate
    0.98
    ittee
    0.97
     nominated
    0.97
     hearings
    0.94
     appointments
    0.93
     nominee
    0.92
    Activations Density 0.092%

    No Known Activations