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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 12253
    Prev
    Next
    INDEX
    Explanations

    relationships to the public figure "Trump" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to Donald Trump and his associates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.77
    zsche
    -0.72
     Cth
    -0.69
     Anarchy
    -0.68
     brute
    -0.66
    sis
    -0.66
    utra
    -0.65
     Boko
    -0.64
    iencies
    -0.63
     ILCS
    -0.63
    POSITIVE LOGITS
     confid
    1.15
     aides
    1.05
     aide
    0.91
     staffers
    0.91
     advisers
    0.89
     administration
    0.87
     adviser
    0.87
     associates
    0.86
     staffer
    0.84
     campaign
    0.83
    Activations Density 0.274%

    No Known Activations