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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 20850
    Prev
    Next
    INDEX
    Explanations

    news-related entities and events such as news agencies, countries, dates, and official statements

    oai_token-act-pair · gpt-3.5-turbo

    references to official statements and sources in news articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Purchase
    -0.75
    Newsletter
    -0.74
    \\\\\\\\
    -0.70
    onom
    -0.68
    ||||
    -0.67
    Ö
    -0.63
    --------------------------------
    -0.61
     calcul
    -0.60
    ////////////////////////////////
    -0.59
    --------------------
    -0.59
    POSITIVE LOGITS
     Reuters
    0.87
     AFP
    0.87
     Kremlin
    0.82
    AFP
    0.78
     watchdog
    0.75
     REUTERS
    0.72
     Tehran
    0.71
     WikiLeaks
    0.70
     POLITICO
    0.70
    usalem
    0.67
    Activations Density 0.750%

    No Known Activations