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

    Neuronpedia

    APICircuit 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. 10-RES-JB
    6. 3902
    Prev
    Next
    INDEX
    Explanations

    Breaking news-related words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "breaking news."

    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
     nostalg
    -0.79
     haun
    -0.69
    inav
    -0.66
    haps
    -0.65
    rendered
    -0.64
    vag
    -0.63
     sul
    -0.63
     maj
    -0.62
     expressive
    -0.62
     phased
    -0.60
    POSITIVE LOGITS
     Emails
    1.44
    Desk
    0.80
     Brief
    0.72
    NEWS
    0.71
     MFT
    0.70
     Latest
    0.70
     Desk
    0.70
     Mub
    0.68
    Catholic
    0.67
    email
    0.66
    Activations Density 0.032%

    No Known Activations