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. 17507
    Prev
    Next
    INDEX
    Explanations

    phrases related to political parties

    oai_token-act-pair · gpt-3.5-turbo

    references to political party leadership and 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
     voy
    -0.75
    sea
    -0.74
    obar
    -0.73
    su
    -0.70
    iffin
    -0.68
    Oracle
    -0.67
    olphins
    -0.66
    abytes
    -0.66
    tnc
    -0.66
     visitation
    -0.65
    POSITIVE LOGITS
     nominate
    0.95
     Caucus
    0.92
     caucus
    0.89
    isans
    0.86
    udeau
    0.84
     nominating
    0.83
     elected
    0.83
    kefeller
    0.81
    Liberal
    0.80
     centrist
    0.79
    Activations Density 0.560%

    No Known Activations