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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1348
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "news" at high activation levels

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to news and reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mutually
    -0.65
    istically
    -0.64
     rapists
    -0.64
     rapist
    -0.62
     goodwill
    -0.62
     Reconstruction
    -0.62
     unarmed
    -0.61
     disarm
    -0.60
    sighted
    -0.59
    uras
    -0.59
    POSITIVE LOGITS
    chool
    1.02
    ews
    1.00
    ource
    0.96
     VIDEOS
    0.91
    hower
    0.89
    peed
    0.89
    atcher
    0.86
    ystem
    0.86
    ashington
    0.86
    velt
    0.85
    Activations Density 0.006%

    No Known Activations