© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1842
    Prev
    Next
    INDEX
    Explanations

    references to news reports or articles mentioning certain events or claims

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.85
    creen
    -0.77
    ophers
    -0.75
    ificial
    -0.72
    educ
    -0.70
    knife
    -0.69
     palate
    -0.69
    otin
    -0.69
    benefit
    -0.69
    egal
    -0.68
    POSITIVE LOGITS
     reports
    0.90
     reporting
    0.80
    è¦ļéĨĴ
    0.78
    ounces
    0.75
     Newsweek
    0.74
     Reporting
    0.71
     headlines
    0.69
     Reporter
    0.69
     Reports
    0.69
     Stories
    0.69
    Activations Density 0.054%

    No Known Activations