© 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. 10-RES-JB
    11. 11147
    Prev
    Next
    INDEX
    Explanations

    mentions of the publication "The Daily"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Daily" in reference to various media outlets

    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
    imately
    -0.83
    NetMessage
    -0.74
    lessly
    -0.72
    holes
    -0.70
    boa
    -0.70
    obal
    -0.69
    eca
    -0.66
    dropping
    -0.63
    laus
    -0.63
    */(
    -0.62
    POSITIVE LOGITS
     Beast
    1.23
     Caller
    1.19
     Mail
    1.10
    Mail
    1.05
    motion
    1.02
     Telegraph
    1.00
    mail
    0.92
     Meal
    0.91
     Herald
    0.91
    Beast
    0.90
    Activations Density 0.024%

    No Known Activations