© 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. 0-RES-JB
    11. 8278
    Prev
    Next
    INDEX
    Explanations

    phrases in Tagalog, especially those related to conveying a message or instruction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "na" and its variations in different contexts

    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
    ATTLE
    -0.89
     Hayward
    -0.71
    ributes
    -0.70
    urous
    -0.66
    actic
    -0.66
     Sounders
    -0.65
     Weston
    -0.64
    VR
    -0.64
    enton
    -0.62
    Seattle
    -0.61
    POSITIVE LOGITS
     na
    3.88
     Na
    1.43
     ka
    1.25
    Na
    1.22
     ni
    1.14
     ja
    1.14
     ng
    1.10
     va
    1.09
     awa
    1.06
     NA
    1.04
    Activations Density 0.019%

    No Known Activations