© 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. 0-RES-JB
    11. 22381
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific news outlet named "Daily"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Daily"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    seq
    -0.87
     weld
    -0.71
    ink
    -0.66
     abstraction
    -0.66
    ude
    -0.65
     ported
    -0.64
    ess
    -0.64
    aeus
    -0.64
    ame
    -0.64
    ../
    -0.64
    POSITIVE LOGITS
     Daily
    3.71
    Daily
    3.13
    daily
    2.36
     Weekly
    1.87
     daily
    1.70
     Evening
    1.50
     Times
    1.47
     Monthly
    1.46
     Everyday
    1.39
     Huffington
    1.38
    Activations Density 0.013%

    No Known Activations