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. 21772
    Prev
    Next
    INDEX
    Explanations

    words with the term "so-called."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the term "so-called," indicating a skepticism or critique of labels or classifications

    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
    =-=-=-=-
    -0.90
    =-=-=-=-=-=-=-=-
    -0.82
    erves
    -0.78
     unden
    -0.78
    =-=-
    -0.76
     istg
    -0.74
     destro
    -0.69
    *=-
    -0.69
    Ö¼
    -0.68
     proport
    -0.67
    POSITIVE LOGITS
    called
    0.83
    erred
    0.82
    untarily
    0.77
    holes
    0.72
    metadata
    0.72
    calling
    0.72
    amn
    0.72
    call
    0.71
    unt
    0.70
    nant
    0.69
    Activations Density 0.023%

    No Known Activations