© 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. 10-RES-JB
    11. 2695
    Prev
    Next
    INDEX
    Explanations

    information related to media attention, interviews, controversial events, lawsuits, and communication forms such as emails and phone calls

    oai_token-act-pair · gpt-3.5-turbo

    references to forms of communication and media attention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilty
    -0.81
    vantage
    -0.80
    portion
    -0.77
    width
    -0.76
     Radius
    -0.75
    Size
    -0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    thy
    -0.74
    ãĤ¨ãĥ«
    -0.72
    radius
    -0.72
    POSITIVE LOGITS
     interviews
    1.39
     speeches
    1.35
     petitions
    1.34
     conferences
    1.32
     briefings
    1.30
     declarations
    1.27
     presentations
    1.27
     announcements
    1.26
     seminars
    1.25
     lectures
    1.25
    Activations Density 0.364%

    No Known Activations