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. 1-RES-JB
    6. 15508
    Prev
    Next
    INDEX
    Explanations

    mentions of "The Wall Street Journal"

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Wall Street Journal"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tumblr
    -0.65
    rav
    -0.65
    netflix
    -0.61
    speed
    -0.60
     ours
    -0.60
     favour
    -0.60
    ourcing
    -0.59
    ardless
    -0.59
    rown
    -0.59
     theirs
    -0.59
    POSITIVE LOGITS
     Journal
    1.13
     Journals
    1.01
    ournals
    0.97
    Journal
    0.94
     Sentinel
    0.89
    eers
    0.85
     Gazette
    0.84
     Editors
    0.84
     journal
    0.83
     Observer
    0.79
    Activations Density 0.006%

    No Known Activations