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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 17770
    Prev
    Next
    INDEX
    Explanations

    phrases related to news outlets and online publications

    oai_token-act-pair · gpt-3.5-turbo

    references to media organizations and their content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dame
    -0.65
     DAR
    -0.64
    ère
    -0.62
    agos
    -0.61
     Gou
    -0.60
    lda
    -0.59
     declass
    -0.59
     remarks
    -0.59
     colonel
    -0.58
     testified
    -0.58
    POSITIVE LOGITS
    Magazine
    0.99
    Month
    0.98
    Subscribe
    0.92
    Reader
    0.88
     Subscribe
    0.82
    Week
    0.82
     Podcast
    0.81
     Weekly
    0.79
    Article
    0.77
     Newsletter
    0.76
    Activations Density 0.205%

    No Known Activations