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. 17580
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific political figure named Aquino

    oai_token-act-pair · gpt-3.5-turbo

    the word "Aquino" and its variations in the context of political discussions

    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
    nesday
    -1.01
    chool
    -0.85
    matically
    -0.82
    lished
    -0.80
    Ö¼
    -0.76
    ĸļ
    -0.73
    anks
    -0.72
    lessness
    -0.70
    owship
    -0.70
    alities
    -0.70
    POSITIVE LOGITS
    zzi
    1.05
    ero
    1.02
    etti
    0.92
     Rossi
    0.89
    opsis
    0.82
    chi
    0.81
    ensis
    0.79
    oco
    0.78
    eno
    0.77
    ctions
    0.76
    Activations Density 0.022%

    No Known Activations