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. 9-RES-JB
    6. 824
    Prev
    Next
    INDEX
    Explanations

    references to the historical figure Joseph McCarthy, known for McCarthyism

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "McCarthy" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "McCarthy" and to some extent references to communism

    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
    wright
    -0.94
    strings
    -0.89
    hower
    -0.87
    ems
    -0.81
    string
    -0.77
    ables
    -0.75
    fulness
    -0.74
    manship
    -0.73
    book
    -0.73
    ouri
    -0.73
    POSITIVE LOGITS
    ãĥ£
    0.75
     onions
    0.71
     Osw
    0.70
    ohydrate
    0.70
    rint
    0.69
     negatives
    0.65
     Bloody
    0.64
     gelatin
    0.64
     positives
    0.63
    é¾
    0.63
    Activations Density 0.132%

    No Known Activations