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. 9-RES-JB
    6. 7812
    Prev
    Next
    INDEX
    Explanations

    mentions of news sources like "The Washington Post" followed by specific content or author names

    oai_token-act-pair · gpt-3.5-turbo

    references to articles or publications, specifically from "The Washington Post."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -0.79
     secondly
    -0.72
     util
    -0.71
    5000
    -0.68
     enqu
    -0.68
     Whilst
    -0.65
    wards
    -0.64
     SQ
    -0.63
    course
    -0.63
    tons
    -0.63
    POSITIVE LOGITS
     POLITICO
    0.93
     Caption
    0.84
    CLOSE
    0.70
    Washington
    0.70
     nonpartisan
    0.69
    ASHINGTON
    0.68
    Republicans
    0.68
    CNN
    0.67
    VERTISEMENT
    0.67
     Washington
    0.66
    Activations Density 0.253%

    No Known Activations